diff --git "a/results.json" "b/results.json" --- "a/results.json" +++ "b/results.json" @@ -8,7 +8,7 @@ "family": "Indo-European", "flores_path": "eng_Latn", "fleurs_tag": "en_us", - "commonvoice_hours": 2658.0, + "commonvoice_hours": 2659.0, "commonvoice_locale": "en", "in_benchmark": true }, @@ -44,7 +44,7 @@ "family": "Indo-European", "flores_path": "spa_Latn", "fleurs_tag": "es_419", - "commonvoice_hours": 446.0, + "commonvoice_hours": 447.0, "commonvoice_locale": "es", "in_benchmark": true }, @@ -80,7 +80,7 @@ "family": "Indo-European", "flores_path": "fra_Latn", "fleurs_tag": "fr_fr", - "commonvoice_hours": 1054.0, + "commonvoice_hours": 1055.0, "commonvoice_locale": "fr", "in_benchmark": true }, @@ -128,7 +128,7 @@ "family": "Indo-European", "flores_path": "rus_Cyrl", "fleurs_tag": "ru_ru", - "commonvoice_hours": 243.0, + "commonvoice_hours": 244.0, "commonvoice_locale": "ru", "in_benchmark": true }, @@ -236,7 +236,7 @@ "family": "Austroasiatic", "flores_path": "vie_Latn", "fleurs_tag": "vi_vn", - "commonvoice_hours": 6.1, + "commonvoice_hours": 6.2, "commonvoice_locale": "vi", "in_benchmark": true }, @@ -620,7 +620,7 @@ "family": "Indo-European", "flores_path": "nld_Latn", "fleurs_tag": "nl_nl", - "commonvoice_hours": 115.0, + "commonvoice_hours": 117.0, "commonvoice_locale": "nl", "in_benchmark": true }, @@ -656,7 +656,7 @@ "family": "Atlantic-Congo", "flores_path": "yor_Latn", "fleurs_tag": "yo_ng", - "commonvoice_hours": 6.0, + "commonvoice_hours": 6.1, "commonvoice_locale": "yo", "in_benchmark": true }, @@ -1292,7 +1292,7 @@ "family": "Indo-European", "flores_path": "cat_Latn", "fleurs_tag": "ca_es", - "commonvoice_hours": 2847.0, + "commonvoice_hours": 2852.0, "commonvoice_locale": "ca", "in_benchmark": true }, @@ -1376,7 +1376,7 @@ "family": "Turkic", "flores_path": "uig_Arab", "fleurs_tag": null, - "commonvoice_hours": 366.0, + "commonvoice_hours": 367.0, "commonvoice_locale": "ug", "in_benchmark": true }, @@ -2360,7 +2360,7 @@ "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 2.6, + "commonvoice_hours": 2.7, "commonvoice_locale": "ibb", "in_benchmark": false }, @@ -3524,7 +3524,7 @@ "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 11.0, + "commonvoice_hours": 12.0, "commonvoice_locale": "tig", "in_benchmark": false }, @@ -3560,7 +3560,7 @@ "family": "Abkhaz-Adyge", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 31.0, + "commonvoice_hours": 37.0, "commonvoice_locale": "kbd", "in_benchmark": false }, @@ -4028,8 +4028,8 @@ "family": "Bookkeeping", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": null, - "commonvoice_locale": null, + "commonvoice_hours": 0.0, + "commonvoice_locale": "iba", "in_benchmark": false }, { @@ -4616,7 +4616,7 @@ "family": "Turkic", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 12.0, + "commonvoice_hours": 13.0, "commonvoice_locale": "sah", "in_benchmark": false }, @@ -4976,7 +4976,7 @@ "family": "Indo-European", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 0.0, + "commonvoice_hours": 0.5, "commonvoice_locale": "kvx", "in_benchmark": false }, @@ -5420,7 +5420,7 @@ "family": "Indo-European", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 0.0, + "commonvoice_hours": 0.2, "commonvoice_locale": "kxp", "in_benchmark": false }, @@ -5432,7 +5432,7 @@ "family": "Indo-European", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 0.0, + "commonvoice_hours": 0.1, "commonvoice_locale": "gjk", "in_benchmark": false }, @@ -6224,7 +6224,7 @@ "family": "Abkhaz-Adyge", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 67.0, + "commonvoice_hours": 68.0, "commonvoice_locale": "ab", "in_benchmark": false }, @@ -7616,7 +7616,7 @@ "family": "Indo-European", "flores_path": null, "fleurs_tag": null, - "commonvoice_hours": 12.0, + "commonvoice_hours": 13.0, "commonvoice_locale": "kw", "in_benchmark": false }, @@ -8170,6 +8170,116 @@ "type": "Open", "license": "Llama3.3", "creation_date": "2024-11-26" + }, + { + "id": "meta-llama/llama-3.1-70b-instruct", + "name": "Llama 3.1 70B Instruct", + "provider_name": "Meta", + "cost": 0.3, + "hf_id": "meta-llama/Llama-3.1-70B-Instruct", + "size": 70553706496.0, + "type": "Open", + "license": "Llama3.1", + "creation_date": "2024-07-16" + }, + { + "id": "meta-llama/llama-3-70b-instruct", + "name": "Llama 3 70B Instruct", + "provider_name": "Meta", + "cost": 0.4, + "hf_id": "meta-llama/Meta-Llama-3-70B-Instruct", + "size": 70553706496.0, + "type": "Open", + "license": "Llama3", + "creation_date": "2024-04-17" + }, + { + "id": "mistralai/mistral-small-3.1-24b-instruct", + "name": "Mistral Small 3.1 24B", + "provider_name": "Mistral", + "cost": 0.3, + "hf_id": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", + "size": 24011361280.0, + "type": "Open", + "license": "Apache 2.0", + "creation_date": "2025-03-11" + }, + { + "id": "google/gemini-2.0-flash-001", + "name": "Gemini 2.0 Flash", + "provider_name": "Google", + "cost": 0.4, + "hf_id": null, + "size": null, + "type": "Commercial", + "license": null, + "creation_date": "2025-02-05" + }, + { + "id": "google/gemma-3-27b-it", + "name": "Gemma 3 27B", + "provider_name": "Google", + "cost": 0.2, + "hf_id": "google/gemma-3-27b-it", + "size": 27432406640.0, + "type": "Open", + "license": "Gemma", + "creation_date": "2025-03-01" + }, + { + "id": "qwen/qwq-32b", + "name": "QwQ 32B", + "provider_name": "Qwen", + "cost": 0.2, + "hf_id": "Qwen/QwQ-32B", + "size": 32763876352.0, + "type": "Open", + "license": "Apache 2.0", + "creation_date": "2025-03-05" + }, + { + "id": "deepseek/deepseek-chat-v3-0324", + "name": "DeepSeek V3 0324", + "provider_name": "DeepSeek", + "cost": 1.1, + "hf_id": "deepseek-ai/DeepSeek-V3-0324", + "size": 684531386000.0, + "type": "Open", + "license": "Mit", + "creation_date": "2025-03-24" + }, + { + "id": "microsoft/phi-4-multimodal-instruct", + "name": "Phi 4 Multimodal Instruct", + "provider_name": "Microsoft", + "cost": 0.1, + "hf_id": "microsoft/Phi-4-multimodal-instruct", + "size": 5574460384.0, + "type": "Open", + "license": "Mit", + "creation_date": "2025-02-24" + }, + { + "id": "amazon/nova-micro-v1", + "name": "Nova Micro 1.0", + "provider_name": "Amazon", + "cost": 0.14, + "hf_id": null, + "size": null, + "type": "Commercial", + "license": null, + "creation_date": "2024-12-05" + }, + { + "id": "anthropic/claude-3.5-sonnet", + "name": "Claude 3.5 Sonnet", + "provider_name": "Anthropic", + "cost": 15.0, + "hf_id": null, + "size": null, + "type": "Commercial", + "license": null, + "creation_date": "2024-10-22" } ], "scores": [ @@ -8319,93943 +8429,3391 @@ }, { "model": "openai/gpt-4o-mini", - "bcp_47": "es", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.4226799078177409, - "sentence_nr": 0 + "score": 0.15815751066481462, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "es", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5651672709988255, - "sentence_nr": 0 + "score": 0.5152611872266766, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.32406433662077544, - "sentence_nr": 0 + "score": 0.07407154448063642, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5243586266504104, - "sentence_nr": 0 + "score": 0.43145434527321425, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.34633672321253084, - "sentence_nr": 0 + "score": 0.12903696060775005, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5378805625051344, - "sentence_nr": 0 + "score": 0.456225988032654, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ar", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.5077888484472814, - "sentence_nr": 0 + "score": 0.12369892692249995, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ar", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6493197366069867, - "sentence_nr": 0 + "score": 0.44549610902403686, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.4318843329340524, - "sentence_nr": 0 + "score": 0.06647168102389285, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6011096108554106, - "sentence_nr": 0 + "score": 0.34350832619898364, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.3582301850807646, - "sentence_nr": 0 + "score": 0.12560672881768975, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5380305837807603, - "sentence_nr": 0 + "score": 0.4969560260291519, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ur", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.3732667150787326, - "sentence_nr": 0 + "score": 0.12422788549118892, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ur", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5674650482249737, - "sentence_nr": 0 + "score": 0.40222210564426, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.4641883721676649, - "sentence_nr": 0 + "score": 0.09735981717515908, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.6403267149729506, - "sentence_nr": 0 + "score": 0.35288934658906385, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.300740577257699, - "sentence_nr": 0 + "score": 0.08273178236238297, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5272774705181614, - "sentence_nr": 0 + "score": 0.36399666460809255, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fr", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.3576035471132581, - "sentence_nr": 0 + "score": 0.38870674200492367, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fr", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5426399702952437, - "sentence_nr": 0 + "score": 0.6484380084879691, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.4422044705926463, - "sentence_nr": 0 + "score": 0.3961285597009415, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.6089032707320831, - "sentence_nr": 0 + "score": 0.6148751441350505, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.3099603853356145, - "sentence_nr": 0 + "score": 0.4923751299732868, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5209233176748354, - "sentence_nr": 0 + "score": 0.6853756490381199, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "bn", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.33210944907163426, - "sentence_nr": 0 + "score": 0.11133996756497437, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "bn", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5289420578289948, - "sentence_nr": 0 + "score": 0.4410280353998367, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.4331131003868224, - "sentence_nr": 0 + "score": 0.17374951565433233, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5898969623074624, - "sentence_nr": 0 + "score": 0.45325597884524305, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.35580399268816465, - "sentence_nr": 0 + "score": 0.17743299460161885, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5392592206305507, - "sentence_nr": 0 + "score": 0.43071271897416463, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "pt", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.4475435253337274, - "sentence_nr": 0 + "score": 0.26459538953931094, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "pt", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5956867226653717, - "sentence_nr": 0 + "score": 0.5272178908335121, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.5274220384037692, - "sentence_nr": 0 + "score": 0.26801022984888695, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.6765588140322357, - "sentence_nr": 0 + "score": 0.5654883864995515, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.39317381456022266, - "sentence_nr": 0 + "score": 0.21665407194210906, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.6026058740561834, - "sentence_nr": 0 + "score": 0.4344921442639243, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "pa", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.4166560818400039, - "sentence_nr": 0 + "score": 0.38249626297768063, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "pa", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.6515522498665886, - "sentence_nr": 0 + "score": 0.40976234193505356, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.42734667499155, - "sentence_nr": 0 + "score": 0.7281051247089317, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.6397906518456509, - "sentence_nr": 0 + "score": 0.7882997401328445, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.48930936408255293, - "sentence_nr": 0 + "score": 0.5806197937310393, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.699085629239476, - "sentence_nr": 0 + "score": 0.7346706700987636, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ru", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.37224644590020084, - "sentence_nr": 0 + "score": 0.08635800047213174, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ru", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5716341952568125, - "sentence_nr": 0 + "score": 0.218109371254876, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.36921945860245514, - "sentence_nr": 0 + "score": 0.25552199116069907, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5602656572610939, - "sentence_nr": 0 + "score": 0.3799133205289109, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.3963410285961713, - "sentence_nr": 0 + "score": 0.23386786214190372, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.613166190285915, - "sentence_nr": 0 + "score": 0.3682311523733465, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sw", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.3660623361610902, - "sentence_nr": 0 + "score": 0.5642761727828352, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sw", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5840165124966731, - "sentence_nr": 0 + "score": 0.6181373706707737, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.4404175157492415, - "sentence_nr": 0 + "score": 0.4093301993048525, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.6499400950194552, - "sentence_nr": 0 + "score": 0.512762518189388, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.44294247711132617, - "sentence_nr": 0 + "score": 0.6244631487487835, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5915660675216782, - "sentence_nr": 0 + "score": 0.6931369519059803, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "id", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.500516497336299, - "sentence_nr": 0 + "score": 0.8003203203844999, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "id", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.7019407549121803, - "sentence_nr": 0 + "score": 0.9453478043428296, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.40306183496110326, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.6065077241830509, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.3756985486608933, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5991443770283833, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "de", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.4824471894538444, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "de", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6756807439055712, - "sentence_nr": 0 + "score": 0.629039349740581, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.4892530408936975, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6697286007212407, - "sentence_nr": 0 + "score": 0.629039349740581, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.5009456904181451, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6893719644090858, - "sentence_nr": 0 + "score": 0.629039349740581, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ja", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.23363375253301555, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ja", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.4539275409654266, - "sentence_nr": 0 + "score": 0.49546288984677567, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.498687604330117, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.6495577010231699, - "sentence_nr": 0 + "score": 0.43795381992037963, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.18273944860385094, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.44261865187418153, - "sentence_nr": 0 + "score": 0.5881561248602009, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "te", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.30519601919508343, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "te", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.48440897375540304, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.3897372020625521, - "sentence_nr": 0 + "score": 0.2887138086538547, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5520780806464591, - "sentence_nr": 0 + "score": 0.6342291345998248, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.2153742037697241, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.4581737688885401, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mr", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.34655442187135127, - "sentence_nr": 0 + "score": 0.47410002229034043, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mr", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6023567722379627, - "sentence_nr": 0 + "score": 0.7538467008030766, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.2775751476798985, - "sentence_nr": 0 + "score": 0.5087473540251254, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5467407840471017, - "sentence_nr": 0 + "score": 0.7647955332172516, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.3372953649368346, - "sentence_nr": 0 + "score": 0.5087473540251254, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5482505380106469, - "sentence_nr": 0 + "score": 0.7647955332172516, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "jv", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.2453787991485662, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "jv", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.4099668999237371, - "sentence_nr": 0 + "score": 0.2828367156737383, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.2988083057066004, - "sentence_nr": 0 + "score": 0.48181149445310956, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.4973008562914265, - "sentence_nr": 0 + "score": 0.7675828789334244, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.28528905353056333, - "sentence_nr": 0 + "score": 0.5091224918749461, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.4885812318466243, - "sentence_nr": 0 + "score": 0.7829685247145245, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "vi", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.3091536050099401, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "vi", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.504963808447426, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.35120509380099896, - "sentence_nr": 0 + "score": 0.7511573912724299, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5127991322787522, - "sentence_nr": 0 + "score": 0.9453473543978153, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.2935204022158406, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.4867597973247361, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ta", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.41613344165345995, - "sentence_nr": 0 + "score": 0.19464521962073492, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ta", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5740077532098984, - "sentence_nr": 0 + "score": 0.5838790966762375, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.49132868804528823, - "sentence_nr": 0 + "score": 0.3390387389794623, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6524450166860349, - "sentence_nr": 0 + "score": 0.6170420596680538, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.2929684584911775, - "sentence_nr": 0 + "score": 0.3142665434344143, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5038324436049059, - "sentence_nr": 0 + "score": 0.6466526067220029, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fa", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.49428478171113605, - "sentence_nr": 0 + "score": 0.4216890913810254, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fa", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.6360862650323953, - "sentence_nr": 0 + "score": 0.6885217194158456, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.27106784138456536, - "sentence_nr": 0 + "score": 0.5014756677893482, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.458287745564531, - "sentence_nr": 0 + "score": 0.7958858211784339, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.4034224234291925, - "sentence_nr": 0 + "score": 0.6255340042200862, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5736798834726872, - "sentence_nr": 0 + "score": 0.8724783049357475, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "tr", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.3109058809229358, - "sentence_nr": 0 + "score": 0.1582866049832572, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "tr", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5045951829816013, - "sentence_nr": 0 + "score": 0.34487142413575794, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.2822871796543221, - "sentence_nr": 0 + "score": 0.17905278399134197, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5208915029538709, - "sentence_nr": 0 + "score": 0.37257295447029826, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.1077205146963877, - "sentence_nr": 0 + "score": 0.15521606028436608, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.428338145564396, - "sentence_nr": 0 + "score": 0.37645329404497957, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "yue", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.2556346494160282, - "sentence_nr": 0 + "score": 0.08860973467526746, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "yue", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.4538035440310274, - "sentence_nr": 0 + "score": 0.3178004360288637, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.4102082155233312, - "sentence_nr": 0 + "score": 0.1418524086391329, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5474039587505726, - "sentence_nr": 0 + "score": 0.38295770773758747, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.22327767951697297, - "sentence_nr": 0 + "score": 0.15268019045355535, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.4063556880747369, - "sentence_nr": 0 + "score": 0.41028757620299977, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ko", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.2392120773016637, - "sentence_nr": 0 + "score": 0.19074380068002203, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ko", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.440445343487272, - "sentence_nr": 0 + "score": 0.40566585096277824, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.22424453668984448, - "sentence_nr": 0 + "score": 0.17382347640129553, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.41637444107955873, - "sentence_nr": 0 + "score": 0.4061580777885601, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.2572733200413211, - "sentence_nr": 0 + "score": 0.13868172938464635, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.4520014138562526, - "sentence_nr": 0 + "score": 0.3094469764260441, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "it", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.40487199173556226, - "sentence_nr": 0 + "score": 0.13410301071131794, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "it", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5637204315528265, - "sentence_nr": 0 + "score": 0.3942932268034351, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.40165053057541866, - "sentence_nr": 0 + "score": 0.598931508663349, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5837756195280097, - "sentence_nr": 0 + "score": 0.7353063745802827, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.40311197004738203, - "sentence_nr": 0 + "score": 0.30677064886592076, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5788525108956781, - "sentence_nr": 0 + "score": 0.5308555945242818, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fil", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.5108628809804742, - "sentence_nr": 0 + "score": 0.17328174803055044, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fil", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6929396211173784, - "sentence_nr": 0 + "score": 0.3178268797869574, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.49872195941208947, - "sentence_nr": 0 + "score": 0.4262221594184117, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6907054265096231, - "sentence_nr": 0 + "score": 0.5886657414856064, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.45313578977486535, - "sentence_nr": 0 + "score": 0.286608441075188, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.6160993561903745, - "sentence_nr": 0 + "score": 0.4579283646292802, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "arz", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.3335262554878992, - "sentence_nr": 0 + "score": 0.3315037521841549, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "arz", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5258955094447381, - "sentence_nr": 0 + "score": 0.468197879470805, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.3411271681324882, - "sentence_nr": 0 + "score": 0.43186481103649477, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.5323123267352375, - "sentence_nr": 0 + "score": 0.5792139686527714, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.2651736858432996, - "sentence_nr": 0 + "score": 0.30890092021323623, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.4491383344282561, - "sentence_nr": 0 + "score": 0.5553909583113487, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "gu", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.37742688647401873, - "sentence_nr": 0 + "score": 0.20972571494011877, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "gu", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5674314405993244, - "sentence_nr": 0 + "score": 0.395894071208527, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.24828430598240606, - "sentence_nr": 0 + "score": 0.18559542135951204, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5078550622606068, - "sentence_nr": 0 + "score": 0.3804842882867387, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", + "bcp_47": "en", "task": "translation_from", "metric": "bleu", - "score": 0.34545319957597864, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", + "bcp_47": "en", "task": "translation_from", "metric": "chrf", - "score": 0.5727052860304503, - "sentence_nr": 0 + "score": 0.35369375385786006, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "th", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.339818403012025, - "sentence_nr": 0 + "score": 0.12475846123062707, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "th", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5156759219303986, - "sentence_nr": 0 + "score": 0.27823340731817514, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.4381699512774638, - "sentence_nr": 0 + "score": 0.15122189206102096, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5887410281104106, - "sentence_nr": 0 + "score": 0.26750110507308866, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", + "bcp_47": "zh", "task": "translation_from", "metric": "bleu", - "score": 0.38968867962607934, - "sentence_nr": 0 + "score": 0.10759927692349745, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", + "bcp_47": "zh", "task": "translation_from", "metric": "chrf", - "score": 0.5581403039390647, - "sentence_nr": 0 + "score": 0.21065794536310511, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "kn", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.12843096555088776, - "sentence_nr": 0 + "score": 0.30327872414714485, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "kn", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.3356201430079791, - "sentence_nr": 0 + "score": 0.49804213541579834, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.17727473966694943, - "sentence_nr": 0 + "score": 0.21685485833927476, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.3475071694578125, - "sentence_nr": 0 + "score": 0.3714219747170047, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", + "bcp_47": "hi", "task": "translation_from", "metric": "bleu", - "score": 0.20451416608402828, - "sentence_nr": 0 + "score": 0.12274092982883021, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", + "bcp_47": "hi", "task": "translation_from", "metric": "chrf", - "score": 0.38185285396290036, - "sentence_nr": 0 + "score": 0.3385513651938691, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3536676112393946, + "score": 0.5745954681260859, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5252283198216768, + "score": 0.7920051188244848, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.5494025263062274, + "score": 0.6358921902612438, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.6860161543947312, + "score": 0.8041899227402122, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.2636405082687104, + "score": 0.6299285159340671, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5072009470421238, + "score": 0.7993134129243716, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.2348553453946444, + "score": 0.3572514590810421, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.4891959123914518, + "score": 0.40312319760122833, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.4222656487192343, + "score": 0.35059076445515835, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.6421614792137705, + "score": 0.40219803477483124, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.20174173621464261, + "score": 0.41316127706749806, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5179166118048267, + "score": 0.4430321339435623, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.3461114139111442, + "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.5537111972654953, + "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.353179331599201, + "score": 0.8780634320789833, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.5558881348090785, + "score": 0.926946700115022, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.33522833358360765, + "score": 0.7964573357809173, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.534195929930943, + "score": 0.8458636471716781, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3734491516745214, - "sentence_nr": 0 + "score": 0.28822910320599077, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5499493819792871, - "sentence_nr": 0 + "score": 0.6087031937056202, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.4397415106513502, - "sentence_nr": 0 + "score": 0.3880515884750121, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5907735810868658, - "sentence_nr": 0 + "score": 0.6587916715823183, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.31308824228412185, - "sentence_nr": 0 + "score": 0.5142726846179982, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.4950165423717857, - "sentence_nr": 0 + "score": 0.7344716263345912, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.3612717557348476, - "sentence_nr": 0 + "score": 0.4094748015187699, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5558371668340614, - "sentence_nr": 0 + "score": 0.4288513205758089, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.46890796443667687, - "sentence_nr": 0 + "score": 0.4487746167679644, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.6445795993451092, - "sentence_nr": 0 + "score": 0.4476730201191672, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.30704694388456133, - "sentence_nr": 0 + "score": 0.2836623400057614, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5217468869740803, - "sentence_nr": 0 + "score": 0.29147337237183046, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.41661325369918395, - "sentence_nr": 0 + "score": 0.16950698451288215, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.587715140145979, - "sentence_nr": 0 + "score": 0.48668984177868246, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.3937759330018993, - "sentence_nr": 0 + "score": 0.2113054108348111, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.5961746226614889, - "sentence_nr": 0 + "score": 0.44238229987470284, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.4088174428659509, - "sentence_nr": 0 + "score": 0.26207903587847736, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.5924365007019256, - "sentence_nr": 0 + "score": 0.50073123223194, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.16285971091078436, - "sentence_nr": 0 + "score": 0.6837528314895732, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.43885470392891923, - "sentence_nr": 0 + "score": 0.7968789890147058, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.37339369029886144, - "sentence_nr": 0 + "score": 0.7017829861193574, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5432112723704581, - "sentence_nr": 0 + "score": 0.7743327021667388, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.23751632756038837, - "sentence_nr": 0 + "score": 0.6961795371760597, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.4414396968637268, - "sentence_nr": 0 + "score": 0.7859480663394858, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.21791041776703116, - "sentence_nr": 0 + "score": 0.2360941227140328, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.44004369960566136, - "sentence_nr": 0 + "score": 0.35939098278145853, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.46773190351581395, - "sentence_nr": 0 + "score": 0.14118350058219528, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.6215065422343401, - "sentence_nr": 0 + "score": 0.20431837779877604, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 + "score": 0.1811004938014804, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.2799135631577256, - "sentence_nr": 0 + "score": 0.2649993136544717, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 + "score": 0.23649053182388327, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.2035993189596312, - "sentence_nr": 0 + "score": 0.4127382174759535, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.13511029141047634, - "sentence_nr": 0 + "score": 0.20721924345714232, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.36856155052346085, - "sentence_nr": 0 + "score": 0.36475932190367044, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 + "score": 0.11386607947762988, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.17779867452221493, - "sentence_nr": 0 + "score": 0.33564583347921473, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.20075037608245913, - "sentence_nr": 0 + "score": 0.8107492451395732, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.4313422346882818, - "sentence_nr": 0 + "score": 0.900032747778274, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.1874333361540541, - "sentence_nr": 0 + "score": 0.8761560783209453, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.41793053821849296, - "sentence_nr": 0 + "score": 0.9484564543183253, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3716703379730988, - "sentence_nr": 0 + "score": 0.7505336182671021, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5800216707448408, - "sentence_nr": 0 + "score": 0.8401910628269498, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.15080316480304565, - "sentence_nr": 0 + "score": 0.13725861056573663, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.4424628792965376, - "sentence_nr": 0 + "score": 0.11147384852362276, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.2777349520199055, - "sentence_nr": 0 + "score": 0.13453927150397377, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5312509449503231, - "sentence_nr": 0 + "score": 0.10522974272748564, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.20390263030337064, - "sentence_nr": 0 + "score": 0.22055493694673897, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.4345747929502553, - "sentence_nr": 0 + "score": 0.3931965048763613, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.17913113678266074, - "sentence_nr": 0 + "score": 0.839587623092576, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.39874837064673946, - "sentence_nr": 0 + "score": 0.9096086668952811, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.39725392028587103, - "sentence_nr": 0 + "score": 0.6885326214539055, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.5469018582137435, - "sentence_nr": 0 + "score": 0.8229812189228393, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 + "score": 0.839587623092576, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.3532549308527307, - "sentence_nr": 0 + "score": 0.9096086668952811, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3625318570509803, - "sentence_nr": 0 + "score": 0.8003203203844999, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5303179877188419, - "sentence_nr": 0 + "score": 0.9453478043428296, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.35328951154883514, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5286973900062114, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3816118513389601, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5423632561644341, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.4427412215990632, - "sentence_nr": 0 + "score": 0.7215691881328408, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.6222208791908107, - "sentence_nr": 0 + "score": 0.735100789804592, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.3709917965006414, - "sentence_nr": 0 + "score": 0.4765874091118851, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.6015654773262525, - "sentence_nr": 0 + "score": 0.45911557772276623, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.3899394268518547, - "sentence_nr": 0 + "score": 0.45022125383821326, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.594841687625348, - "sentence_nr": 0 + "score": 0.46874267375238576, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.23150269995638142, - "sentence_nr": 0 + "score": 0.2028736642487601, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.46961020207805865, - "sentence_nr": 0 + "score": 0.43458947791319813, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.23712278533862596, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.5116265380743877, - "sentence_nr": 0 + "score": 0.3013901676230198, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.16820174403705807, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.4159468803310715, - "sentence_nr": 0 + "score": 0.38106012955734714, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.30495379106243414, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.503838460756843, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.5238129782835811, - "sentence_nr": 0 + "score": 0.2887138086538547, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.6833665118503387, - "sentence_nr": 0 + "score": 0.6342291345998248, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3682745409081855, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5329336102063273, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.09425983742608171, - "sentence_nr": 0 + "score": 0.20748131961458333, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.32871133484905984, - "sentence_nr": 0 + "score": 0.2716205232346228, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.1500767455847696, - "sentence_nr": 0 + "score": 0.37589902061551017, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.35247049201056063, - "sentence_nr": 0 + "score": 0.42554151277542873, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 + "score": 0.20748131961458333, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.25911153048152963, - "sentence_nr": 0 + "score": 0.2716205232346228, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 + "score": 0.4135171000263379, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.1714827465806386, - "sentence_nr": 0 + "score": 0.7050151549073953, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.20461279328052204, - "sentence_nr": 0 + "score": 0.42988105429544615, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.40700264333409225, - "sentence_nr": 0 + "score": 0.7577244658187771, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.022279489478813384, - "sentence_nr": 0 + "score": 0.5366411241731205, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.1674529343985772, - "sentence_nr": 0 + "score": 0.825566494253596, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.4763809450534613, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.6797378130452167, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.36983487280597815, - "sentence_nr": 0 + "score": 0.7511573912724299, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5775204256764592, - "sentence_nr": 0 + "score": 0.9453473543978153, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3926191044336021, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5853598001081626, - "sentence_nr": 0 + "score": 1.0, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.4865718767050507, - "sentence_nr": 0 + "score": 0.3450219162509876, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.6519330394001581, - "sentence_nr": 0 + "score": 0.3993348853061597, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.4961186750382622, - "sentence_nr": 0 + "score": 0.5561195823338172, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.6420056154822653, - "sentence_nr": 0 + "score": 0.5362935676066722, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.4047209070683015, - "sentence_nr": 0 + "score": 0.5803515898273521, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5746231903096143, - "sentence_nr": 0 + "score": 0.5422220468910552, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.20522978206415157, - "sentence_nr": 0 + "score": 0.2562150245540302, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.4816367810257562, - "sentence_nr": 0 + "score": 0.47046477830594896, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.2607066928529267, - "sentence_nr": 0 + "score": 0.33438299066966715, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.5190821165076681, - "sentence_nr": 0 + "score": 0.5409759573191787, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.3651499702707945, - "sentence_nr": 0 + "score": 0.37854068916316835, + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.539793217489328, - "sentence_nr": 0 + "score": 0.5743796566387722, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.4416835863595156, - "sentence_nr": 0 + "score": 0.44711013370113256, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.623117008858419, - "sentence_nr": 0 + "score": 0.7319347493436125, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.4249436481722545, - "sentence_nr": 0 + "score": 0.49023502313124495, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.6187144317500936, - "sentence_nr": 0 + "score": 0.7638414724136195, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.3867569653562107, - "sentence_nr": 0 + "score": 0.4424906782646928, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5709420484876131, - "sentence_nr": 0 + "score": 0.705507971295129, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.621898873312397, - "sentence_nr": 0 + "score": 0.21326369102393236, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.7757345897028827, - "sentence_nr": 0 + "score": 0.24781828193168487, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.5494249598159933, - "sentence_nr": 0 + "score": 0.07860105393900486, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.7465246513770903, - "sentence_nr": 0 + "score": 0.09678377693633947, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.5335140114876958, - "sentence_nr": 0 + "score": 0.11601141307045003, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.7053320460577175, - "sentence_nr": 0 + "score": 0.21671187566850864, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.1659862741557369, - "sentence_nr": 0 + "score": 0.2577716972449781, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.4884440880714965, - "sentence_nr": 0 + "score": 0.5171901208397282, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.40269672228447434, - "sentence_nr": 0 + "score": 0.35015224715252113, + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.6225404903248234, - "sentence_nr": 0 + "score": 0.5701648579139658, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.3695995811393786, - "sentence_nr": 0 + "score": 0.3349252032650068, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.6148303949607244, - "sentence_nr": 0 + "score": 0.5908087431574293, + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.2917184142654506, - "sentence_nr": 0 + "score": 0.22816849039973935, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5624937546502969, - "sentence_nr": 0 + "score": 0.5295534280606148, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.2373642291509686, - "sentence_nr": 0 + "score": 0.348007986647201, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.521644947712484, - "sentence_nr": 0 + "score": 0.6148736550683231, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.2712572779797431, - "sentence_nr": 0 + "score": 0.31222258402876674, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5422335579149541, - "sentence_nr": 0 + "score": 0.5549937870516303, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.42143379809685383, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5946121916131629, - "sentence_nr": 0 + "score": 0.10721126066665879, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.4141553414774169, - "sentence_nr": 0 + "score": 0.23683075175361493, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5906263169622974, - "sentence_nr": 0 + "score": 0.2631328190836655, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.20087168885945464, - "sentence_nr": 0 + "score": 0.0, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.38939667381078735, - "sentence_nr": 0 + "score": 0.16455392433653304, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.19552775795890473, - "sentence_nr": 0 + "score": 0.36033217429111203, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.3925483761400883, - "sentence_nr": 0 + "score": 0.5707860320039717, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.24101134936111826, - "sentence_nr": 0 + "score": 0.461597801606675, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.42220180022908466, - "sentence_nr": 0 + "score": 0.6280777654467244, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "bleu", - "score": 0.22800980663874482, - "sentence_nr": 0 + "score": 0.4224298950114519, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", + "bcp_47": "hi", + "task": "translation_to", "metric": "chrf", - "score": 0.4539695239053247, - "sentence_nr": 0 + "score": 0.60823085524287, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.2364242732935431, - "sentence_nr": 0 + "score": 0.43103580001357805, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.5166025885857578, - "sentence_nr": 0 + "score": 0.6690742226623104, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.21954964295787202, - "sentence_nr": 0 + "score": 0.6031612036218008, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.48436759393641593, - "sentence_nr": 0 + "score": 0.736286703381354, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "bleu", - "score": 0.5054426458074261, - "sentence_nr": 0 + "score": 0.39432344823662835, + "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", + "bcp_47": "en", + "task": "translation_to", "metric": "chrf", - "score": 0.6722694706437392, - "sentence_nr": 0 + "score": 0.5943452555220106, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "bleu", - "score": 0.33382920003857136, - "sentence_nr": 0 + "score": 0.10772332006118607, + "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", + "bcp_47": "zh", + "task": "translation_to", "metric": "chrf", - "score": 0.5343019280932326, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3885821466849501, - "sentence_nr": 0 + "score": 0.17652714369664665, + "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5985448528428169, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.35162367832688185, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5470403853789135, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.25066959615472983, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4464863544842361, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.24634920227044405, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4663964950094987, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.2030779777377279, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.433265414942881, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.3969548673353603, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.6084494342072353, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.44834209038718303, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.6192927072328505, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.4059702785610718, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.5924126044868774, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.4540422742824559, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.6751320303512911, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.5339026027654551, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.7303050277242, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.45382991587984656, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.6795124822993059, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.1518030911347623, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.03947087289497203, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.24871772534163297, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.15503659808176187, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.0019920318725099606, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.3259608048468566, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.546117067949716, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1658740169858733, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4024808935109278, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.28031528470622435, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5080912630709646, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.43161598042102073, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.575098943836209, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.23322806032691942, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4970157115640211, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.32434551072073575, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.5461576315951293, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.417842986003915, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6235945624226917, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.4684582258807146, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6509870807795504, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.37892189586155534, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5908052258359918, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.3354557799221337, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5828616357620534, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.38540591321276524, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.6091815498132347, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.2913871477484173, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4778519392615073, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.3859000637680225, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5858315307170925, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.3738636268027588, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5633496484582216, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.3850293035436385, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.5627108155348461, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.36775365397595855, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.5429838358858414, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.3742787779358338, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.5507724077862277, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.2042633250999265, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4024854380942464, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.21682957830342386, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.40328066851151617, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.17569336234053629, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.13989491400872253, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4095257685037439, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.37645276051115606, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5980216031532829, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.22917125225310467, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.47903700624901113, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.02228851669741669, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.16941662225476226, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.15925566245534395, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.020022039661695485, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.18319796614102749, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.18337542465784618, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2738250966440318, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.17457751379065342, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.2364341169976402, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.44688068305416384, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3275794528853699, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.490529412998314, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3910557548848884, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5640234702218941, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.33493420443764327, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5494512089523403, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.18258051379187495, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.37144982797514564, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5566300649554314, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.35425134311526146, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.543224327229853, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.3446263661390609, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.5457062469198075, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.1844277711083256, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.39231379751700163, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.10142265089946709, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.23765231683034127, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.13326254700682963, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.37783345527529155, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0836098993777203, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.28681946123560914, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.23361580096963977, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.4620323651475797, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.2464000786532921, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.44961038359873023, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.2761854595042038, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.505027473861755, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.06850339366064954, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.2947252945949938, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.20218909354463535, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.1512699697277094, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.3128685016104829, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.15815751066481462, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.5152611872266766, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.07407154448063642, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.43145434527321425, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.12903696060775005, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.456225988032654, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.12369892692249995, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.44549610902403686, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.06647168102389285, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.34350832619898364, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.12560672881768975, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4969560260291519, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.12422788549118892, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.40222210564426, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.09735981717515908, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.35288934658906385, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.08273178236238297, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.36399666460809255, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.13714845589364738, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.45499281593451946, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.11564012893219777, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.44599783682350064, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.12601482779921785, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.43595665254608706, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.3026566818840519, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.5945859352092411, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.2521233582161207, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.40959087443621306, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.6348509381122925, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.07793031063789554, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.3700181221537743, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.0867932999243575, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.4201964133235075, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.08214106568089705, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.3969463877642616, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.41649654108052436, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3630576975795868, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0744904632040495, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4111163205685468, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.08767210132815903, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.40476518002703893, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.08616711094288851, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3696512763473903, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.12894104034845807, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4486368934849452, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.14738500064905094, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.4659728395318289, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.15386029327005746, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.43911482594829104, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.10070927557742705, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.43718220262892105, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3370100422576744, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.1946966569103724, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0772718393063023, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.4203683137304257, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.09084091756463074, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.4286741659142759, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.06126604215610123, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.3837677428398438, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.0756907193511249, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.4138725093679467, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.16764957347186446, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.1195053737774238, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.4512136289975786, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.21748353646757182, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.4462746462826943, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4331286519146886, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.3538966478758119, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4179644538349004, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.11378204941109882, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.4981472095171313, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.43759229210123524, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.10505106462290037, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.4474870048911137, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.1059352062327485, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.4291550754056065, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.4239838444198129, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.0009218289085545725, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.15720527174368754, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.47882285385622714, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.3374178992279451, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.15653859793617866, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.43177798053127925, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0982484177591637, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4109236039282987, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.10106439835419144, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.44450926478634867, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0891537192318598, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3970634926176537, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.16496711525651045, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.052359103292999656, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3805982553288677, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0950136506275681, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4372017487229785, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.12506460115047335, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.46140175133635725, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.4404222773455128, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.1259356760989446, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.44568274520971096, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.10127171102984855, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.4525620764847558, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.10833971870416897, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.4467303749319595, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.16322494183480127, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.4815584993817062, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.14163299203710986, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3958314877752854, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.09463828889338871, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3398200805270262, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0904087252785689, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.41830513174690515, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.1200100437012302, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4636227306109079, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.17208141302168437, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4542522451167506, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.21351902664706998, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5130443042033361, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.06289570792563275, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.3813881170279124, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.38763756150559275, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.16269986423611488, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.19045679700622437, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.4124342444810736, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.2398247112527542, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.06939838145153245, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.05275923024775565, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.3724723203846839, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.3544628606759813, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.3371547585108182, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.12650809806003369, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.4579202271851988, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.09676230489828269, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.43266369498706486, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.1691386174483793, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.4920789340026317, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.19135523280427486, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.49947805136320467, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.2356661678654945, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.5124350706386419, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.14944432524273302, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.4972796478830659, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.10588612806056373, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4068718481729766, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.10720391954020723, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.37219605281253065, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.09793316925795417, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4297577431879659, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.0967458811247473, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.4485783191522753, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.06851723496815999, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.40911149660575097, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.14184998906630783, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.44498159653494584, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.13308739447486365, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3932447622969156, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.36741937011390374, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.11220450894323894, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.46129962837218175, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.3645369664653625, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.3275292968031138, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.08932983819566953, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.37462132890676997, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.15453746478246141, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.4413516563123831, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.1383193561213217, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.4229717720106369, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.14846392828893068, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.44939103256256696, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.10713148568717314, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.41522111700393083, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.3539070801331386, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.11340129142744679, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4168800407013454, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.3702987017023586, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.3241317524160092, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.07351652222518425, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.3862617013651048, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.30718853768673293, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.3499024158832446, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.12587301409115934, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.43278573034203477, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.4312123024580457, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.24946780875926136, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.06500924965575555, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.389301118498321, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.29873361351172023, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.08186981924084771, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.36422083962860535, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.07752927781917028, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.3238609427019678, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.3092395616495983, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0811151580341062, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.4179228886149028, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.04318453178079916, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.3381884955798567, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.15333726274185422, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.14176967102285878, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.15856726741880453, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.06061016244701235, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.3480533968220821, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.3107132702855867, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.06622410994100032, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.42506963891617355, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.08459573412751416, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.4172605432414846, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.08986406706995408, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.44470674434718094, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.4109749814872678, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.07565762629954577, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.3606232238015037, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.12594843055469976, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.4353555563309006, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.07142908588092715, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.3642310370662869, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.3186898662502609, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.06656213940646744, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.3842510919126927, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.06946125044973972, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.37972229376763555, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.15996142821020284, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.42995669154818883, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.06922310590511903, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.39694083278594716, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.1339039164909805, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.44979655276903346, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.16234678312329395, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.4114313966468408, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.14108777831558816, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.38610201135781486, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.07152747748412269, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.38927458491364797, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0889604331153271, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4174106361046784, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.35972456016417403, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0857750978817917, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.44136113805162547, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.29764050036303846, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2883740704360469, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2604470328007762, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.2750949112536697, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.369396410785335, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.30886876402238045, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3445489778722215, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.22034235744543199, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3992343412084987, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.12454093367377822, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.45400457519342263, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.29211251612445716, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.08742637130044478, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3782754387193616, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.3843618124722185, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.10567309578898446, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.4024349171516437, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.32603788130544104, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.13894512516215204, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.483078120317575, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.0832724096908118, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4097982251907115, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.09843551021314972, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.44345815368179514, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.15357179047039304, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4395965605263733, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.3352216651363677, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.2926736955448575, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.058474735537506775, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.346711996349685, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.32876484301179987, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.14849717699290216, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.4416362145529488, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.0862684017016977, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.46311606179286086, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.08054744999594665, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.3910533825433727, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.42292922955918455, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.14370950122782516, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.3334514572265135, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.21268091254698024, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.12067839739874531, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.3233637515119462, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.31176467991525436, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.08160236983918483, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.38567653709947824, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.3636314071779547, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.07352808725672978, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.39849401484916575, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0948243550653547, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.40688622415675096, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.37941443386230733, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0754791629755296, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4115037991203147, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.17376142320673926, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4494840281694199, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.09628144140511948, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.3988415038006601, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.08810203169380636, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4085631076024389, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.3490597215692333, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.363944181125048, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.3406214634850959, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.15565663466238167, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.45102089786807525, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.3349337342755207, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.19306612958933164, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4566094829965023, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.15165087037620367, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.10988031996776393, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.14384707977041108, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.17231483245958562, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.26083297460286664, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.2205187870837211, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0937099995586274, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.38638693017010634, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.06087893264282183, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.30404764547641244, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.41200704988717746, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.109333912337143, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.43946533504329827, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.3875031655866923, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.14527200081334513, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.4245172781893951, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.12099786399361606, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4447762461237164, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.35906265614758676, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.10096459770150681, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4189740217714419, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.15711076787374778, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4926610996660017, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.12253628106911543, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.41098604819939544, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.08517707813747888, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4298965032520897, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.13594665641498668, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.47621282367548656, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.12066287439499573, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.40225318320388664, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.16231893029395061, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.4858308027555531, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3781094023262652, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.052244516140907096, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.351436961102141, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.26865126568707876, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.17419420900027405, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.07291105107725455, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4474906527730671, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.08334085822278188, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.40282723830388284, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.33037125702748205, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.08714838249931423, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.3692825189624461, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.09127577115927074, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.3300669374207929, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3231709973877731, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.1680802224904863, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.08434660455803612, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.32335639685468925, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.909878624371155, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.9494599978334789, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.6484538568755306, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.8387015535622947, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.9625248317849852, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.9799603794887166, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.17236959754271308, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.17066745219661572, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.17964021028231922, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.05270938682743268, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.31252925174187013, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.1075481111616894, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.3738814601144911, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.15334066204940114, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.1179671428128192, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.35902184995166087, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.29668758510830123, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0529715946034933, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.35557346479092056, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.3447636250916266, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.36010213387059153, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.1569159469136538, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.14702176025137792, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.15207203397909086, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.38870674200492367, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.6484380084879691, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.3961285597009415, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.6148751441350505, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.4923751299732868, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.6853756490381199, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.11133996756497437, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4410280353998367, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.17374951565433233, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.45325597884524305, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.17743299460161885, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.43071271897416463, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.26459538953931094, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5272178908335121, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.26801022984888695, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5654883864995515, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.21665407194210906, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.4344921442639243, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.3563758622144919, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6037023613177924, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.3574583793293068, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.5924115119819969, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.37994652561206577, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6464467277069994, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.2158914621804855, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.5448184155666022, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.22292726306270316, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.5653789747970112, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.09362261118571368, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.3452056942265759, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.18031307339768174, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.522164454804456, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.21403222128228389, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.563121432204311, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.18917620656425485, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.4346170232980484, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.2999092588227898, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5505916495384416, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4054983797456263, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6264774230839022, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.420450507904553, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6503146347305717, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4263684749347053, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.20051119758906127, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5334791309401924, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.24894072982768842, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5212235893093335, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.2562849004088193, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.5767019342009202, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.3535002370419364, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.5959879218348465, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.393613605227227, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.6492198447661237, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.2465888500427759, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5221084445696768, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.35983766090218355, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5862251404739759, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.21147734744561483, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.41020178654369294, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.22150370805587954, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.5463488388082953, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.2971752224486841, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.605133664481872, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.2329856851831642, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.5405751250637106, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.39461811323775403, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5655204109921267, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.2786312783602775, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.4836796407825139, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.41756686236967944, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5616829345739638, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.25564177137418986, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.49870011615602194, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.39579112101105834, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.6431490866428237, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.38189567401226293, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.6154314825900052, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.15985840708020788, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.44951053332729884, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.35253338922743144, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.6487975154557831, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.2126707920684064, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.4659908460634765, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.27217589854489177, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.5756343666825848, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.24513414885202045, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.5476647609559218, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.23240102389974368, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.4973274282641141, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.28467215304840787, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.4298052820106505, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.28653528640783255, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.5053636612097852, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.17979384730979156, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.4177311931467539, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.15426765225005337, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.45289625960131974, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.31326946419057006, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.591171976889058, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.1702602472176709, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4366640707779677, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.7096224667917136, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.8862932371217843, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.5294442646627652, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.7281375072835307, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.933651069586263, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.9586507529693243, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.33713757310040376, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5731908178757754, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.4162915990459618, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5970097205621886, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.3816408219023713, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5784105768028126, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.19129143021561437, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.390473445537339, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.25848476545940924, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.4897308313348651, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.18398226639192106, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.37285010531146734, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.27057949011516347, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5644281635271426, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.29851690541541476, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6224209860013706, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.26958884543190903, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5631664732610485, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.24285172240675165, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4655392375590772, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.29796912700911177, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5158892363484622, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4005296397635166, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6201785376974677, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.07276375309803214, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.38861839385008856, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.17377261603583774, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.4342710497791623, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.15956483578595942, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.425693420655628, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.35205535634937346, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5769772651090223, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.33631398011857205, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.6332428715049205, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.2323385180696658, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5019509292309764, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.21108332811806296, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.5847750744232335, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.2453238227047589, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.55017080577881, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.22952177306405494, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.5279520952576137, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.3520774812078196, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.5735788202105873, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.2063529291350913, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.41364248023079064, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.3618488169166299, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.5708179622131996, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.1506914981676572, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.49409850038698094, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.10586140133972588, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.4674053477944039, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.1712766252338756, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.5225554962608486, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.2797290030028961, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5092945860838002, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.2703645496410475, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5129310433304475, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.2709079038456153, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.447458019441992, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.26036802768146033, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.5255752089611478, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.2492031334256811, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.4923163374806021, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.2907608105126149, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.5445465034944268, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.240340920378981, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4624667456597986, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.43104504141832617, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5953439401847398, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.27907188689389983, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5093017176589221, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.35592474790742606, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.5565115125775245, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.20863984464930022, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.45879801940552783, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.2695149221768555, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.4713033964653895, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.27075075499555246, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.5201548999535662, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.27338789256007584, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.5429269981031598, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.2075953797357176, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.4344742362498603, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.2666372228396489, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5839132669613946, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.3703971546860334, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.6509854048597393, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.3020089249326176, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5666791239956741, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.2667836062177809, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.4889374373828587, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.1515551103099189, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.49455791760408774, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.1059786102229136, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.2561557976916047, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.23919877618601593, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.5302876334280949, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.24664751641319077, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.48702383483350364, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.2103019561790119, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.4375454771782611, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.3556610867487636, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.5896623713361566, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.43209473956081024, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.6466471725002415, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.343734330975999, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.5961090979865409, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.260409852867913, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.4693600515228538, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.21544027588567594, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.4576381595573422, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.2545286403887288, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.46127229234959366, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.24874987153684608, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.4814988208653403, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.4140011428776289, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.6412021306400884, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.3759002268420169, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.6120997127625288, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.17716893523927718, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.3125133953892873, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.22843578925939137, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.39333887911230325, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.19035778476657209, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.32011375391986463, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.21529598963807312, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.47472255443386435, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.19319522417917573, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.5294666692683903, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.1876442538016413, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.45717296303154553, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.22319344534343544, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.47255822473411646, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.3431794518924713, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.5291073153069198, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.2075953797357176, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.418796448457094, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.17593291675420053, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.45966885600223345, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.30749506855677367, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.5615365420131465, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.2539342198718324, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.48976692911803554, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.26939482991021874, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.564348572305916, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.28232804221956187, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.639242930472136, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.24677721152898274, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.5655655793718459, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.177282908048097, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5048008630035653, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.24609114091724077, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5163247162943534, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.20586736678432452, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5290915360201753, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.05670064571372339, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.16937000725041657, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.4219264367109449, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.5790052627496669, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.21550905403743137, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.44719679117350436, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.19946335945716726, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5412386252302255, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.27966169949383496, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.537239861484062, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.32980384185673844, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.6175883753955328, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.14382854899355546, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.26400383568118985, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.21514404656488983, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.22551384015559367, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.30538385012782954, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.5121153023805728, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.21889549804942124, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.3940841212708787, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.1882889817107982, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.3522812586532728, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3618488169166299, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6178847628712388, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.431319746325093, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6234382849939584, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3161306379595585, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6012304838142994, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.31487248334376844, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5635244346599635, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.22897967367089514, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5334911242844559, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.26709890828869226, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5042111985234817, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.4218999224827276, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.6489282208332532, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.26356793966181546, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.5191302272110829, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.20298700573422315, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.3905231106721993, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.3563758622144919, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.5746238432846977, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.34637568582379935, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.5514391895148156, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.24720511037119816, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4462551342337241, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.23380867598952562, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4731313764465835, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.32326983669535764, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.5757950493268048, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.2920934313715234, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4983574989743429, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.1529466247397943, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.4275296567755792, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.309848051124064, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.5622431891031534, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.2516768028374535, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.5052262603078841, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.2380050699329688, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.48227504945496735, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.18624263881830802, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.4914113027832365, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.2395446927992299, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.4721484222602001, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.20251299853063762, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.36192674925462354, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.12015228994776961, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.31437848676811814, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.17979384730979156, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.331355254735914, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.3291256332376796, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.5670250015789864, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.3422882142242731, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.5278861608717469, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.38564863816921563, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.4887006722841345, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.2489574113984516, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.5438702135465744, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.25119117418063647, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.5358947011982449, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.24117223077042385, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.512020635779483, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.23020656163897005, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5608590094117443, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.2988707080433144, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5286791480233601, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.29215021962379045, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5527751145536495, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.1931328662607509, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.43550456875371113, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.3394516832204828, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.5487992573856032, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.20801258614305904, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4082367628634589, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.29222881654408056, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.6120984237392771, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.30956660793759877, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.6188773222172356, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.14588825992287732, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.39984326863280045, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.38935973617512226, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.09100730294865149, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4152991006861775, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.12576299804399627, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4275740936545043, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.16421603133867055, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.29137424728903016, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.20812209921683228, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.31687414190905666, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.16498223460029865, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.2972734576062982, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.274614810062371, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5281783547748619, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.18452698284010527, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.37129342404244153, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1649362336939456, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.36964185672093963, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.34396207830145586, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5775887851128505, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.30371045098471633, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.6140790369362206, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.2252297536658673, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.437729946490623, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.3004961314114194, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6112720381807045, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.2668575997365348, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.5174669930427155, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.25289636204048427, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.55030569340461, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.2247327109713433, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5250140675378029, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.3378883984281531, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.6049772225333672, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.2761659300730445, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5565926641426052, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.13384453331197527, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4151425963129396, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.2276261087372084, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5006338961901005, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.20109176688134525, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5208655725098277, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.3003653956261136, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.5819235916814075, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.34009641866679796, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.6387903483458015, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.28509173779340485, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.5531716447251654, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.14651860136741404, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.26874220962782625, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.3014199920541698, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.37258990587027996, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.2169400845409205, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.352650085718584, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.280867833557141, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.47682234542802715, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3195214890612964, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6238377764870237, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.2026004770366011, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4124307729296919, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.3479857106948536, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5434098077482219, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.127094130129695, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.37183060884198066, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.1616475408517619, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.2842078929375233, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.22839293770911745, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4657355446143013, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.1709913567536511, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.29449196775233905, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.13435637642994447, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.34277719024611025, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.19606965736186524, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5029030066686957, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.19598322445625943, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.46665751191230503, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.21170876705481304, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5213888058464138, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.2104347389999275, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.41820208790180724, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.33893526679717595, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5305909471293387, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.4005296397635166, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5780131186067837, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.2534684260065973, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.465022490109088, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.28341626687166926, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4981912496496188, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.18787234368655517, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.43638553308108674, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.19035778476657214, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.3275220698724237, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.2139885278593109, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.5273959990464491, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.16558141211628247, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.37532912975144084, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.11012419619306524, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.4937984099457621, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.14599223028360678, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.4828499846637324, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.12579787892324615, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.46133126472684716, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.1281637706417447, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.22833109825855033, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.25500119387217685, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.42217126960650364, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.29264105234089743, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.36844739850003594, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.38249626297768063, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.40976234193505356, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.7281051247089317, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.7882997401328445, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.5806197937310393, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.7346706700987636, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.08635800047213174, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.218109371254876, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.25552199116069907, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.3799133205289109, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.23386786214190372, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.3682311523733465, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.5642761727828352, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.6181373706707737, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.4093301993048525, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.512762518189388, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.6244631487487835, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.6931369519059803, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.2615858282579583, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.35447530946908884, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.4577275269488853, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6747054474171109, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.25383339228798274, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.45896379476820603, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.15138514598766048, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.3237497764315872, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.27668736912821895, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.4414406760568898, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.17200767571780612, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.3723150838362789, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.15604242268653643, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.2255928425212252, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.4751132438608344, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.6159319815107203, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.1477219991186121, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.28685201698226354, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.24728515687112834, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3088155734423375, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.7281051247089317, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.78479833664205, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3254455687469726, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4474512036484817, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.353203510510529, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4910213297498164, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.4815092081725061, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5820265218174012, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.23887527917609022, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4120359948636439, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.23660362391696813, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.34152697838249696, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.580451128369423, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.7246473808162345, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.580451128369423, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.728208634600343, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.8482942955247808, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.9256238040654331, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.34589895849033114, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.44792042673107413, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.47320724783393625, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.5833006006517599, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.3556521383601747, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.594830811413066, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.19984607356962125, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.29326031481052006, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.08939270118279458, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.2952752522340665, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.21629114799587432, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.3542320138389837, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.27274191069381915, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.37436438971100644, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.580451128369423, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.7246473808162345, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.580451128369423, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.728208634600343, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.2434330428491034, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.31858900384957733, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.583526016818016, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.6994652193905146, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.27405612859390877, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.4639958592456083, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.24007528246707907, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.31084467045503017, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.6052987576779449, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.643602170728296, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.13004800471424346, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.28217142159025543, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.3674668904964848, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.40975628086142124, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.4815092081725061, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.5785251190053333, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.37821486365532614, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.4718665834023439, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3763743474188506, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4120099199050514, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.38694317759010316, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.45827711860455167, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3699382260470039, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4032851361478274, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.23270804908165135, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3478589640284733, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.4115167991342047, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5649900101054287, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.45167594566243024, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5169677927619225, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.22453002699007485, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.3354597455808525, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.24489516889906388, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.409369762090413, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.23386786214190372, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.3780009826926042, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.18341524527739528, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.3989952325675248, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.3925121365052661, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.47788592802001717, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.12789533377801793, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.2283763803651714, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.15896519992112562, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.29513999460654694, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.1423412184218882, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.2596718628394258, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3571150500823898, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.44642876819396304, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3571150500823898, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5018967494794737, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3572188192648703, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.45381175288762937, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.08968235248346597, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.2175311081388801, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.10682827247639556, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.21551117313912851, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.07425055521504613, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.18122341046764998, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.1472462377094902, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.30525310195831357, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.2774527633525211, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.4358323759361012, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.1978585723043446, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.3527599187160617, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.31314224813827346, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.3932583887521134, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.5199302229930708, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.6017481019884499, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.2523019529343173, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.4406369072888057, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.24728515687112834, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.31221693968406194, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.19230188007838597, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.3407021378942239, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.41072675483179805, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.5635589150380774, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.12045422179467957, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.22184013352319704, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.580451128369423, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.6612342258381259, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.3883375900135818, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.4643731845106876, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.33062429129755794, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4887128900317842, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.6064630666233242, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.6712747226800536, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.6242817472465665, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7123666275414222, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.13536681105774234, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.23595972523293418, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.14728954312449322, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.2256490809237466, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.37300331821940047, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.34791594751284466, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4062384532979022, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.7795149903947967, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.8912732146280626, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.6230832293767097, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.6994652193905146, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.33737554588923646, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.369875665962309, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.30389058699653954, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.4310896909809194, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.3763278728427448, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.4261526683335186, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.3924259174695316, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.4246539836622663, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.39022736644855677, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.5202587069271436, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.3672404084841361, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.4518744271362045, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.21027545940631823, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4572185175571455, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.25383339228798274, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.46123461430035645, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.16401798649868696, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.3760928911869727, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.11414633188690328, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.2503197875391322, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.17807129401511626, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.07843772989359644, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.2669076052967215, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.18105048502088059, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.271054087912132, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.3029928206533524, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.45262153733641225, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.43000007605628365, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.5073076708050636, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.16767849550785174, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.32211607665330505, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.3068038152276031, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.17278760032513005, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.3872014058095359, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.1032637856654291, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.12256115024243901, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.1667153530685962, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.2563322947493884, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.17694915875422723, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.20162477784805663, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.4096636937616398, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.18653722013077995, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.21582567264281033, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.16856369030953883, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.17222588358752802, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.17620697694486812, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.3349127944613063, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.49806572776935465, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.643432991222625, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.40515809323728763, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.5449200667389397, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.15285713412458543, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.24746988080227628, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.22777548520508317, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.10845182904139573, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.27825798566245524, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.21004850229269248, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.3447734406041285, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.22743363869750483, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.4248437050568334, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.29579846078012384, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.5170279422640637, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.2512712267295304, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.2928484110896528, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.20723903671796345, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.2746682387996949, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.3626305461419687, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.36369161190356464, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.2539593860148789, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.31852925024650675, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.22650664914012167, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.44021101913103755, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.3039519244807058, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5267184242152971, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.1416851070122953, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.23506726943391335, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.16170884319006984, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.2250265947708922, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.29110362374826554, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.30776997671170997, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5302815626138546, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.355402294764931, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4505070984023486, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.1411791520898124, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2902470444985328, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.2171788734284664, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.33899728453126426, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.1050176352370787, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3096045806359874, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.35423985843000033, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.449850771779881, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.5572806310452209, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.8076383886663636, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.40214612768560637, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.5573169779174251, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.4815092081725061, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.46880886343224853, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.2782546336574456, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.42327771190588576, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.39109158855739823, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.48247427218434713, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.3931807596037881, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3863308383621456, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.4185938787651429, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.46641278921549706, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.4185938787651429, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.46229900712285454, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.0842816865856957, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.2485953030231616, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.21057401113505914, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.08678345215657841, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.2461700872648841, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.26837663158331726, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.36155324846955933, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.580451128369423, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.7246473808162345, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.3525678415060714, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.543942790381318, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.13733894353973466, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.2628097872401104, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.6242817472465665, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.7056438934239434, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.3925121365052661, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.47722987146488, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.3352430929236216, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.37654805257811624, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.37284875432797243, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.46330437039257283, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.14858713442145016, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.26570814480513566, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.2061927630692647, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.28624131346749065, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.47046185035490873, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.6292601141059937, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.25983833013159885, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.3730064448362738, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0926947735155968, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.27152680319064787, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.22886565624051966, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.09769805815777928, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.2758478148913772, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.15867077366552554, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.2515767320274808, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.21300958856758825, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.10629625019345329, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.2894452751925746, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.5181212746323438, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.5589229357546774, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.4093301993048525, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.5295425318265925, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.6244631487487835, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.7155411017347171, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.21333164424828907, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.32785783444873706, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4825755887985002, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5834117627541725, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4427274357129559, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.48566583494323345, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.16312445849704404, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.17349790295171436, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.12765317762547787, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.20795234713221633, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.3615855225145535, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.39302513361762836, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.5136268735913038, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.7004219512590859, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.5793367580502561, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.7183290415445132, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.2677353447271197, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.33809821343395446, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.3414464563275225, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4182681167677125, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.43812558475283875, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.5153914304432097, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.1022763758993479, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.26825052055805815, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.18808242155433705, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3220587874741547, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.1022763758993479, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.2693375138315219, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.08023149270718091, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.279740710493905, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.21330178332703942, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4261888165527193, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.06534434987768793, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.27176767387111833, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.16168270317308941, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.26228540738738376, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.305925215411119, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.3174603493865962, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.465550295868511, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.25430316746203985, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.31361769699186176, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.6242817472465665, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.7056438934239434, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.41072675483179805, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.5635589150380774, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.3514245731837287, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.534130899739072, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.3090705808198716, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4997989608278053, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.3552281813814547, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5479990039688047, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.264371505578968, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3692663913160793, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.40358627497421223, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.15604242268653643, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.35440326623172935, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.13536681105774234, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.29163125383681, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.6052987576779449, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.6809283802101068, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.29580528518835375, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.4152245863377912, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.108043996762779, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.2627337195947467, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.18085702029043885, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.338987683983403, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.12829843029207522, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.2926652353247206, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.16516473320936778, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.11146727460890443, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.29428893607214085, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.10640850690356463, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.2838000569859586, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.12987293870549732, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.28422427146147505, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.14849103164051436, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.30883024781428503, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.1934884374107349, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.40687776179631713, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.24344044484205296, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.36944883808094725, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.16436148154531297, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3129244553794762, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.3545649986147617, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4749542277669906, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.15326140415213751, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3238101789644524, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.18815571743190213, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.375522612679117, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.1543252261021413, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3572407559404224, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.3352430929236216, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.41922948177882463, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.2666090188234886, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4310539878732571, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.4004456831424889, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5299539464991493, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.3398088489694245, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4228308786458922, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.2927926577346015, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4165527532106081, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.27073362211548463, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.3669195863456915, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.10401577613691954, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.17463781885740615, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.27890809547716944, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.14068535649874328, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.21065537154817968, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.09207598308796072, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.24553846741883023, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.21070435913784732, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.1163540245408256, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.2115841789715117, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.218134321293328, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.35541240647259675, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.19105600040048565, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.41505761608077835, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.2064597158958983, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.36557785420213534, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.8003203203844999, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.9453478043428296, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.629039349740581, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.629039349740581, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.629039349740581, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.49546288984677567, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.43795381992037963, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5881561248602009, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.40854152133685306, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.41213231348812146, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.40435987083533204, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.39618802899930716, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.39618802899930716, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.39858613265631837, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.5948724602646328, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.5042211795038526, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.4425973012069069, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.27447938256311044, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.615291848344044, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5516607622642397, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.47160616105623426, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.33762297226992255, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4576529535952892, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5309982646782259, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.2658483576665877, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.6410540990527072, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.24601372576927547, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.6374693500772332, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.1892240568795935, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.6151179643430991, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6562641136790542, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.46426595961938383, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.41238100267720657, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.5705717737418762, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.410846945789476, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.39909989628767284, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.3113878808075066, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.6728506998168392, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.3113878808075066, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.6758978744760765, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.17181529671327242, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5293474685884572, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4425973012069069, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4410492519530161, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4429196299668147, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.3830425592586042, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.3844263765000694, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.3830425592586042, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.1667955161379731, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.5802683403568892, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.23693055763743093, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.6474126202050918, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.1667955161379731, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.5802683403568892, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.4637878319059324, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.6919476196061328, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.3446073377034663, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.7621696379946562, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.3237722713145643, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.7426638026175545, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.13369377363079382, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.25947507140745757, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6659437947666702, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.49342175914364256, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.18842393723950338, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5854975500881314, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.195647514979229, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5725643788499303, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4352628824108997, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.22179945921983923, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.6249971903914197, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5753050684342109, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5116862201536014, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.33494612818381275, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.520472515533923, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.33471616336068044, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.28977907494497107, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6663117339552681, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.2961516536011624, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.7355780986981637, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.2865612242047131, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6433813179203622, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4276859054768592, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.43620605921972144, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3598792258309727, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.4813598669606701, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.5343147728119615, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.5125809225356253, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5963099883424426, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.6245566175148537, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5539920925426138, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.2102369368326755, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.5768887726639784, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.5326397959358325, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.5226572946586268, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.4877445613866086, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.5073395824633415, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.5073395824633415, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.4148097947848928, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.33709347944719925, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.29382595610734974, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.23693055763743093, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7180407770761651, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.3222538601891173, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7495871587703783, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1667955161379731, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5773664661124461, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.3437729074300146, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.30577290788405437, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.3053963874050995, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.14962848372546667, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5531110803538978, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4660343508894544, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.43340932146378, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.20038908500140973, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.6177327642561014, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.21258844131063828, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.6314891370223008, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.15821285888349254, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.6605676082065987, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.5873831965245108, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.5700887051433648, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.5873831965245108, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4133673303529474, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.48231853956144055, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.37314692804855976, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.17694975149532557, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.4902785344040517, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.1892240568795935, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.5196343731603573, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.4254686256509745, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.20793313992045814, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.4271693186358773, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.44583799328544693, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.37030468338190614, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.7587397825317436, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.29420957081163707, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.735955064899578, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.2722589423069702, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.7290399536251687, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.40933226567881303, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.5099813007320333, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.46778058365701697, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.1433583753123658, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.49048115595910957, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.36660871058936323, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.4698447771642698, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.2891112498777974, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.20506702518574138, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.15084092981447839, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.44419236241196947, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.43706010794795863, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.40969772112178865, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.4134635647455475, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3934230844821369, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.3289300072190674, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.32413768919026276, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.34057065677205645, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.21142141714303078, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.43493490557877573, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.28991415068332943, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.2535985303909064, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.41597114236951854, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4350989271447826, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4297476286175239, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.6390929517394389, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.4714767063337979, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.5124045843781208, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4506325776546161, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4754711104013267, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4775280122429458, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.18900427606312895, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2379375267482382, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.1935812904783315, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.5406340703314851, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.2102369368326755, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.5597860306970691, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.2853612459193062, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.18842393723950338, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5854975500881314, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.15774545980684188, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.616730419953906, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.44478883235565975, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.1400373960430748, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.37309390213978083, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3718896131479321, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.17534823156623092, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.4853402799234523, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.32889384774917263, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.2497159712696397, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.5335315304967084, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.42970160394394363, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4370528005274534, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.12716724199879337, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.5690206807396397, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.5038920264146319, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.39818525322365445, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.554411787673542, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.4146222850152668, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.4194210013201768, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.5277042186210706, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.3827580433841417, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.15388831190795366, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.24316286154385877, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.28130650893311265, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.33867507760059357, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.2996031251762614, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.2065195596274271, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.13995623895459872, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.4674855890757815, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.47300840366486596, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6402657401259225, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6478447458847402, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5695248405921098, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.1329604040267493, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4471856677359072, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.452279977058944, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.49816993286090683, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.44863216660495664, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.3302903244452369, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.1342477978716863, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.42511022061090775, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4279977800006272, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.17013461044703918, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.19400141696774292, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.1721293079939147, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4411812923020589, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4179911123724079, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3630314170535937, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.22637359354764466, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.6010070471156334, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5880855470290005, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5535439540882026, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.22894156860669912, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6299487983245466, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.15362208233245514, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6295157857600502, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.18842393723950338, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.5854975500881314, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.3113878808075066, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.6728506998168392, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.6200828204097578, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.2722589423069702, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.658571547163188, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5800922255460801, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5766882097318834, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5800922255460801, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.4666156174173635, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.3893867836646916, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.38246468665452293, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.21732734812103588, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.2673895048733062, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.28158744196562724, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.13678452669387658, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6382466300772751, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.1075467277016126, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5012312009859288, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.44355652237335036, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.40736387061175394, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.37489485923390314, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.21421851674109063, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.15753286601971267, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.21413630439620454, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.30354067465892703, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4283147867664682, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.28583707879882797, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4802701406922108, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.490032576569998, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.47018722626716275, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.2460260310809598, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.17283382641366998, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.20022065596322774, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.14697628025481496, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.24657376730321656, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.291098552209934, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.4263413781248326, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.4359367610984378, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.3562570068438905, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.11383643766535269, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.16579761015459532, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.191825135463227, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.2887138086538547, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.6342291345998248, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.47410002229034043, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.7538467008030766, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.5087473540251254, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.7647955332172516, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.5087473540251254, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.7647955332172516, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.2828367156737383, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.48181149445310956, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.7675828789334244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.5091224918749461, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.7829685247145245, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.44897710722021167, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6862249089515978, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.404727200247809, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6681898017773897, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.40276720463657734, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6529271690805427, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.2704091953828695, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.6207272323003366, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.5379348324975908, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.7703766110349561, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.30188353873287377, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.6086565367747951, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.48181149445310956, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.7675828789334244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.5091224918749461, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.7829685247145245, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.6026286934891149, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.8025775976044891, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4596980088392874, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.713787745993602, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.5896613549548209, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7528914749586836, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4596980088392874, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.713787745993602, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.24706467963183681, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.4801289744823913, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.6766690087429765, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.3272712268138726, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.6272846474183881, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.3665134361137304, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.6118771029352303, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.28489318277723963, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.5764325110247531, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.2981792160679168, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.5788026000794341, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.2799331151961311, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.6471892368478446, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.8142499721936278, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.7012294787544179, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.8478115719875968, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.23114663823833642, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.5786592584609213, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.23713320246552005, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.6106842970161642, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.21690365808279138, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.5384773678665918, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.3060368950930089, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.6736142284622013, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.6888365053466561, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.8656273480576243, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.25711386542134795, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.6088853751738869, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.45307778036928104, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.6935397252637394, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.5069487414732323, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.7801245319017357, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.5695988432761473, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.7516103467926585, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.5072784644062104, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.7361065921505279, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.7196315267102845, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.8835331636515565, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.5072784644062104, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.7361065921505279, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.30752616970214336, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.5976254557718147, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.40157733283424196, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.6532350818978572, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.38091370416670794, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.6438225861756911, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.48181149445310956, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.7046532915279582, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.5091224918749461, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.7202697992734389, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.24363783193706642, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3903594390682207, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6662116837137958, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.6917901740466924, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.8479928839177578, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.6349495142258627, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.7749613594649343, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.4719458927872361, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.6863265729154345, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.5309354663044072, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.6990707992725005, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.31008822704072875, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.31008822704072875, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.1673872929477023, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.4506667273103674, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.224188058954654, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.5978847447208526, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.6917901740466924, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.8479928839177578, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.19920494035049138, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.614209720001149, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.7221847203387323, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.8931067231936596, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.3416581331218724, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6578570934289981, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.6004981752197522, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7644556249154987, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.5072784644062104, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7342525133793019, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4797543511401896, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7240781310560407, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.14107526427034148, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.6401876410870359, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.7526484951226097, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.24914989711092594, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.33057129676705455, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5669225664686625, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.33057129676705455, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5669225664686625, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.6004981752197522, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.7697646564917222, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.5468017145144113, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.7519227909172003, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.6004981752197522, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.7697646564917222, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.8522456714074852, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.9096914044088521, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.617939643800199, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.8356543644789964, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.8492326635760689, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.9027320255916917, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.30042054271881197, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.27720938018510377, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.428047180290638, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.30350690419450826, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.22847893469128855, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.6281881652405527, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7361567090943679, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.569133886912883, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.6834516951654327, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.18951629567590744, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.5515559648122452, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.27249745234058675, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.576487806400357, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.32078739729528816, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.5779838399768712, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.25811803218589047, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.4814564802258215, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.7954823723658209, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.3742893656007335, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.7582803042224814, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.47410002229034043, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.7538467008030766, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.602867050301643, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.8176176657543648, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.5386695403411698, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.17601203382268035, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.47410002229034043, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.671938683171001, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.5206571060403834, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.689324258927, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.4174441728660793, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.6692136096184196, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.3984098807009828, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.636016958488394, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.3984098807009828, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.636016958488394, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.4794224895461657, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.17150296156301634, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.48812954881732445, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.46076979395163187, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.29623686353922923, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.41682189465797687, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.6573099561830166, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.2852636439147137, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.5851048071392815, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.37494051432044967, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.661973437204244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.8522456714074852, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.9096914044088521, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.37494051432044967, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.661973437204244, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.30407761511253945, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.5461499540157965, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.7954823723658209, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.14628563604185, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.4777301300307737, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.14221479650735855, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.31177258041697303, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.4558951086991579, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.26035572673286655, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.40109985662775005, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.4912131536580228, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.19018868394774802, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.5224363928471276, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.2989381657659374, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.3052690053887312, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.19075975291258387, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.46866709139162926, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.7535887063318502, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.20731650338051813, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.30094298890378757, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.5463695830483137, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.4529852871970908, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.6379815839992429, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.4719458927872361, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.6884790828920573, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.6912804407652906, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.8449079689944796, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.47229389414007084, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.7400562860667964, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.5401725898595141, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.717128056256897, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.5401725898595141, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.7219273458493682, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.44353395455270217, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.6913921626327173, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.15821285888349254, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.4716642229159947, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.39537383933343595, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.617311647158499, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.4393606972268638, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.19653306323688033, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.42643704825557327, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.7385191646867102, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.3984098807009828, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.6511785024442115, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.31011575752288345, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.6452682411767686, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.5021277621795815, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.761461458169805, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.32393211943598493, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.6474115867020543, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.1998573974138024, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.48166604565689325, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.5155781222766946, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.14757581190431865, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.4573311375774372, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.8492326635760689, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.9027320255916917, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.8492326635760689, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.9027320255916917, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.8492326635760689, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.9027320255916917, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.30643882011101126, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.6917901740466924, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.8479928839177578, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.480771131185851, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.7032048786770096, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.6358974376699329, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.736661937085844, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.17059573701616795, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.4753746252238087, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.18107197870881736, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.514661439036253, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.1813423031516851, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4972101263590737, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.18107197870881736, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.514661439036253, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.19835441454182887, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.6062730082124886, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.48181149445310956, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.7675828789334244, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.2797830107070484, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.48181149445310956, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.7675828789334244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.4727805712999679, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.7717158158167359, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.39670882908365773, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.5348878791728369, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.27447938256311044, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.5315032895817616, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.39670882908365773, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.5409379877245147, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.1906936342773436, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.5160021246888273, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.2534743707366162, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.6254912096804822, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.36291227725384023, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.33713540983351536, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.6250009083207365, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.5186653964016543, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.6561896817871797, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.40562163465277223, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.2922968824016215, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.48181149445310956, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.7675828789334244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.5091224918749461, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.7829685247145245, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.33573064840973227, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7081054397334158, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.5263595737059831, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7675828789334244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.33573064840973227, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7081054397334158, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.1375101316530452, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.5540102467708582, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012607361988002, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.1897992267368494, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4726855583591889, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.6917901740466924, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.8479928839177578, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.7482524153102477, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.8447038922744422, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.5021277621795815, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.6665605281744408, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.1821163528973126, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.1983544145418289, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4195908478809098, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.27970267298955453, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.32937303862037204, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3124684968073947, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.29948848396607075, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.4341999352730602, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.6745907228091957, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1986589078880532, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.5285168275193599, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.20110004903792847, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.45623478126637707, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.1987777011513927, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.36857838224116973, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.6856616009150279, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.3384653583738009, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.6082869404281873, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.47375069012411286, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.7107240028283889, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.4727805712999679, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.7717158158167359, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.44476089284108944, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6551098696198423, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.5465526716276092, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.8012679276648627, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.4183007445500922, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.6544146882590995, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.4183007445500922, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.6544146882590995, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.41682189465797687, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.647688351711303, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.803154665668484, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.8805305626734038, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.6838626312597372, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.8481552379853444, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.803154665668484, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.8805305626734038, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4462689092414285, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.20323131695812172, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5370679638669973, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.46829007045350673, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.42359095518407164, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.8492326635760689, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.9063898435384111, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.23932595221309674, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4673115526141697, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5227131146872793, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.2046592065585361, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5139378364418256, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.39020358281213624, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2661828424443392, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.165838472529457, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.38908651109487247, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3337972903996398, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.17411036809769512, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5409636216635109, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.4374960951307028, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6840706293465405, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.16679551613797314, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4850274766865928, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.3025029865727436, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5564009706295315, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4651954337860559, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3764940106481337, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4021117013686505, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4152914707667959, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.36466819017308727, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.15942178318590763, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.36039626112317097, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.5942499629418814, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.3078802898940204, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.3292010361291119, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.6484221669130951, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.4246163317880344, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.6675494539138593, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.278093559995945, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.5759531667584591, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.2869208283752505, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.3243192696860874, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.2229529832462866, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.7511573912724299, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.9453473543978153, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.19464521962073492, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.5838790966762375, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.3390387389794623, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.6170420596680538, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.3142665434344143, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.6466526067220029, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.4216890913810254, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.6885217194158456, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.5014756677893482, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.7958858211784339, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.6255340042200862, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.8724783049357475, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.32365795029773287, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6509517796070665, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.48994561421713123, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.7411155087367244, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.48994561421713123, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.7411155087367244, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.44787223195695314, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.7968980206907678, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.5088645484558708, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.6991726442472661, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.4101479464529936, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.7041976254287654, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.4547900039222725, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.6541971428810075, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.23198210427894825, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.630711601223299, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4284945090100314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7164026439677106, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.23198210427894825, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.630711601223299, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.48994561421713123, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.8020845125558708, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.595092211343687, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.7971172820981081, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.4831233610237384, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.7122562458056777, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.44787223195695314, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.7968980206907678, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.32263864160302524, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.6824395076981005, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.5383680940297331, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.786096406361039, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.5383680940297331, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.786096406361039, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.38305978177479755, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6061131723054572, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.24047860794644352, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.58198979036704, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.42221847853238736, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.6656008733100179, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.24047860794644352, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.58198979036704, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.5124776602965491, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.7722874800637285, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.4481489512240194, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.7994721822064033, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.7511573912724299, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.9453473543978153, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.5582775802710993, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.5512324461754572, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.42984824697674956, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.7289444696770301, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.4881010344921759, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.7317734491561229, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.6507561416639396, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.8215788698315908, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.4881010344921759, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.7317734491561229, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.29170205300854224, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.6498499527552988, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.2719326877457978, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.6002086362682414, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.32365795029773287, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.7121135616759211, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.42984824697674956, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.7395804946242599, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.3684981984538114, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.5606332518476288, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.44787223195695314, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7968980206907678, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3201911827891037, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7182383858693244, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4536404448264584, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.8020827133708689, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.35818640176176625, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.723627810424739, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.48994561421713123, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.8084123599808738, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.4545091839935173, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.7166050399790445, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.31671615012203974, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.6782734900436637, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.4812700337596407, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.7668482135865776, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.3370129264673147, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.7096874943799061, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.12648351910430983, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.19910401453355991, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.5815343547138478, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.1624355752882384, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.4952968469712617, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.3766019021279213, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.7318674193893624, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.37489047453628294, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.7155230965848066, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.4831233610237384, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.7807505267551733, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.44787223195695314, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7968980206907678, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.4284945090100314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.7246227738353674, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.5595205105615875, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.8322210048001876, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.3060368950930089, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.6834837188844622, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.3942058093215873, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.6697898834930974, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.3142665434344143, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.6466526067220029, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.1973212456326944, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.4151043049244464, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.3610544299180199, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.49125115898082056, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.3610544299180199, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.49125115898082056, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.23198210427894825, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.630711601223299, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.4284945090100314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.7164026439677106, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.4284945090100314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.7164026439677106, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.6734648419604768, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.7694606959147566, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.8578928092681435, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.9422733087334002, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.30041915229862387, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.5110381669871915, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.4896430866960958, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.6750223515189266, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.42818224355402373, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.4803501444747088, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7417101158248365, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.38687573986922297, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.6514359547109982, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.42105372680687736, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7001171094008295, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.3865584077322271, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.7076640192892537, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.3865584077322271, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.7076640192892537, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.4881010344921759, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.8110307349404526, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.32365795029773287, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.7121135616759211, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.42984824697674956, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.7395804946242599, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.527528099078667, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.23972125922151485, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.6266330371317139, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.42195777059677314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.7076271819674439, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.42195777059677314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.7128603669502883, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.20390514683548702, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.6152907875442002, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.42062888241722096, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.6813469636986809, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.2600960555023324, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.31671615012203974, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.6782734900436637, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.3942058093215873, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.6294033705157869, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.3942058093215873, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.6452705345581219, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.4909101855057947, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.39545121937832856, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.6541357656856408, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.43281826407421803, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.1974694070034893, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.5383680940297331, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.786096406361039, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.4787974949414673, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.713332477096005, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.44787223195695314, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.7968980206907678, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.44787223195695314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.7968980206907678, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.6576054208318073, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.4536404448264584, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.8020827133708689, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.24237768532177115, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.39469536234609737, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.5917048915180981, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.15824382329465247, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.4020801848996587, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.1835554260049945, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.4427324890847145, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.2491316630275714, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.20312835120509382, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.4762668365393059, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.3407563025626974, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.6104226554223803, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.6407363191582277, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.6966460917682386, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.2719326877457978, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.5963825614997932, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.5595205105615875, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.8322210048001876, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.5595205105615875, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.8322210048001876, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.4770529960418919, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.19268479640608693, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.49975293173596386, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.15083364266523736, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.4907822977105627, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.35818640176176625, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.723627810424739, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.4896430866960958, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.7980971476599384, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.48994561421713123, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.8084123599808738, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.2765896733581188, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5826805982089127, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.43483587481573205, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.6723935384652386, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.27080524311589804, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5735629822442805, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.21576146358278564, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.5673560872668851, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.39545121937832856, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.636466558635705, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.21576146358278564, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.5673560872668851, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.38513414673376833, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.7005713730032203, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.5383680940297331, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.786096406361039, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.38513414673376833, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.7005713730032203, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.11385032360134208, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4382795902467684, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.1365189729052536, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4259340541380412, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2815871636550668, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.2250861242438523, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.5618434465935181, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.3238579233802238, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.6198368821194998, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.512336215207795, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.4481489512240194, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.8131857452490882, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.5124776602965491, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6265447017943011, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.6730489965212471, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.7670434817254471, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.4896430866960958, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6807294776537712, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.39469536234609737, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.6937261271262425, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.60585154759089, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.7547619819808454, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.4812700337596407, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.6942705518980387, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.42195777059677314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.6687475942312653, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.435949382480739, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.7673284019128814, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.435949382480739, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.7335705336375569, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.29715678881302643, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.661467129406907, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.4464617303464354, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.7099628979634083, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.3843832649911012, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.6360002062017179, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.3675667565747676, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.5575264207911254, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.42221847853238736, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.7096175474139502, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.2033897418920923, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.551556930942916, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.42062888241722096, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.6825498124526633, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.31771674795486515, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.6823632455739186, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.5397323593778651, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.8110662878512482, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.5383680940297331, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.786096406361039, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.38918346804460413, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.21644311639014951, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.4550086560720594, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.33188010562448456, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.2919394073770869, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.6265777781732258, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.5383680940297331, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.786096406361039, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.40982224146042756, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.48156738796358634, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.7671994551643374, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.7590994812356263, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.857390040146912, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3113612721440885, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.6244179228679348, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.19857943409196785, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4841638348150365, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.24456656109396324, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.502026173233975, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.1427404270947385, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.3766019021279213, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.6426846682861654, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.3767656346408826, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.33807764768133375, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.71426422535372, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.44701617851855957, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.8047183456557263, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.421151249507493, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.7602108728496834, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.6507561416639396, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.7392285437932827, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.3062859135460401, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.6540898825644205, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.6507561416639396, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.7392285437932827, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4356925719771587, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.16246736614250729, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.38605159790728016, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3026944877822123, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.48994561421713123, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.8084123599808738, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.30752616970214336, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.662093020699087, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.511075227027215, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5741842828404965, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5335784441425054, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.32263864160302524, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6529241277890402, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.4896430866960958, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.7410529316463808, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.4896430866960958, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.7638521785649908, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.4881010344921759, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.73719964992947, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.4797543511401896, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.7030838074817461, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.435949382480739, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7673284019128814, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.4284945090100314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.7199991365237522, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.5971070986250356, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.8874294965619517, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.17855149299161596, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.5203115480779714, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.17855149299161596, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.5366596515222662, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.1832567180568652, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.46874652173038095, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.5019033159973346, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3882810705699302, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3200586334957503, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.17020807300741128, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3763693611344683, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.6360504215730572, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4909326710993637, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.20760470031302655, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.42791815571433417, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.413948387915005, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.6536628131390233, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.5391491945473402, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.703591887429203, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.17202650214787163, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3503510714510492, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.39058393006987374, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.16261055653267345, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3574935801968696, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.16405809898807555, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.21644311639014951, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5575527454538532, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.24248545140243574, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5768340234336301, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.4284945090100314, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.7164026439677106, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.39569555015790975, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.6841500930430788, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.45653838513939016, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5463837424085701, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.48994561421713123, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.8084123599808738, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.2076047003130265, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.5791447789263454, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.2821801681960571, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.5343486909870273, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.19408883848117267, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.38305978177479755, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.6457837185727413, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.2764205123105664, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.5109316705796892, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.5109316705796892, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.5109316705796892, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.5370788574666518, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.45798136636926595, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.18814785746917081, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.5307880463310148, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.1582866049832572, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.34487142413575794, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.17905278399134197, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.37257295447029826, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.15521606028436608, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.37645329404497957, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.08860973467526746, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.3178004360288637, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.1418524086391329, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.38295770773758747, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.15268019045355535, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.41028757620299977, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.19074380068002203, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.40566585096277824, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.17382347640129553, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.4061580777885601, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.13868172938464635, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.3094469764260441, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.22381487678101888, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.5249370100068887, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.09431297723472011, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.3616856339096348, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.11091252683001185, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.26607634610445896, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.10666682719585797, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.33462901494141756, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.14557808399334188, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.36598346755702993, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.18154954789336694, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.4557483776072868, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.20198948917565754, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.34858221035657466, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.16780109158842918, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.3968694014697679, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.1381751568911733, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.3121557499162649, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.22669486951066523, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4484451941575473, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.11697642623186386, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.37117753637984835, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.20065115069964384, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4084885616013531, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.09916009482330297, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3032928217006101, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.13805615693046389, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.40787998733941394, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.12291219097556666, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3448002180666873, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.09478705591775652, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.33293232395887284, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.19148282873929853, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.4707949702068854, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.20608572305725564, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.4704943905570542, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.14057105892389254, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3028381427383384, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.12157241570357182, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.4080990097991491, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.085416483900781, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.2825804066750608, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.13635319583999642, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.2850432830231861, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.16431887969160053, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.4088971379214799, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.11452508920842025, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.3212742401272785, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.06070088845782673, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.2584364364927186, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.15184278721506198, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.4093399937921707, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.15478222669012726, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.3550584759508654, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.1054433514098504, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.2840946641780818, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.16758563722627876, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4598125962895632, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.07875433150726119, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.2638954513805452, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.12768613576122964, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.3279857505284436, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.18041700926694673, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.43852448917973136, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.10734088848154077, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.33946796348247366, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.16136987880724096, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.33626920748765377, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.15197436941722972, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.37271000364127155, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.17795920517030017, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.41862955401967455, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.13230039635238258, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.3269392904147474, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.20266988583156875, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.48179719155586864, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.19388048412249795, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.44361702376789247, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.17544176680792672, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3246583081139427, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.17337747588904887, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3602154895924569, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.1237012344369667, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.33331866832253354, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.09199306870423013, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.22163854171424513, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.20923298022634812, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4391664941823773, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.15589802574348086, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.37894206802233305, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.06089987261870556, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.2933161562815446, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.13303798096767047, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.3647236067340644, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.1948502778967486, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.35525815981538433, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.14391826157279944, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.3239832814361818, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.1769688060281599, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.43047038034793145, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.1618333627385132, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.3458746996740858, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.10027955093430833, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3650503321876689, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.171833798351082, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.4265037420578645, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.17393111207515277, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.39042812195808824, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.15998665872195003, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.35681333217176553, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.22922072303609867, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5075702211165173, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.19064689695123957, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.36954921822756504, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.3141794892548087, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.11397867508647329, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.4390501380282409, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.1785851272602057, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.3800733399524004, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.20219794591777904, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.4267163836239083, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.18851320324917495, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.4118109845203767, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.20113943179758872, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5054929215592371, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.16558784557611658, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.4099467657500184, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.06638301361073934, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.33617826818768626, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.07088281524771703, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.1725752257112697, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.09337623404557584, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.255517984683644, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.23272041020266335, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.5347837552430531, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.11901413329120636, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.2908877283991857, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.11889226114628741, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.27239589447707985, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.15964995175974525, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3581305879558541, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.15593857496482408, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3832822126692406, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1101341452220285, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.27185902677547247, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.14086598242600956, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.36137008859982034, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.21107720643690867, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.43911506176829573, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.15873502699291203, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.37163016195847015, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.16084008820568224, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.49453446122836875, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.13827947882974537, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.4010585707766239, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.1046814649445003, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.35929100435813716, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.1605078796467662, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3607284417441162, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.054452721416611755, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.17786113214625052, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.12832094336767122, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.3205905925059277, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.25513503948815797, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.5313546358608554, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.13788203160207568, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.3107655646435926, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.11215442765734894, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.31037546676327293, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.1634286453435278, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.3969874268891194, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.19418939219609221, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.3901489832573322, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.10180741374280794, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.35728563956947634, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.1945423193070673, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4706222268986097, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.2080824447945289, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4427653693519822, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.06928783103636403, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.28222804846457444, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.1334077033965181, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.3538599860218621, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.12768405545127823, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.27604666315815635, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.15282474172999858, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.3332497402594901, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.15757286670204007, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.3806769190392542, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.05441383188454176, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.24018232621879906, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.10490012364788723, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.33660463773341737, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.11899511888513169, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.4352142502284442, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.12579975046393374, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.404341788822506, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.9087119657256413, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.9560455759500431, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.130164515743941, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.34629605922390666, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.16831858516266504, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.4055923540305375, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.10548435635950038, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.3216875314121515, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.03878009660847357, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.18823804107102407, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.1048945915828233, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.2682365472098696, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.06705104400125081, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.10364481526694266, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.14245697322261636, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.31264665723789214, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.11764506340202335, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.33221255414061107, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.03174814557417323, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.22677038600489324, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.11813127408984, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.33360638121733993, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.12452426344763672, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.33397340303561174, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.19483286033292496, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3818604583347797, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.18262512815371146, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.3793372141796691, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.20118989409590474, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.4568193159296443, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.1463728853883045, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.31232598846995213, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.18601317791265554, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.3622769931215066, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.10134296554489586, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.36352625085241486, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.056826643919713225, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.2266491488847452, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.11586860285558973, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.34426859851631064, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.11537817464773759, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.3235971362772825, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.06766231174629671, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.2969445272858798, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.15459585401418227, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.3893244765025937, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.14329939975046438, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.4108923582650918, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.074972966125329, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.24626763305506796, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.14039526843208108, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.32365712589934936, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.17760506260243636, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.3876268199476132, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.11133338686962291, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.35573855512815966, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.03901477466571775, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2037012862266554, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.06637842065802063, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.21920740076602796, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.1449164009012341, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3465082189188072, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.013978194191220837, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.14269295464324133, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.385707323503979, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.1637184523716508, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.4161934605653721, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.10348510007232478, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.262284085504438, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.2592475459062113, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4431845520770858, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.10490171797384476, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4224966678718647, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.05551337802991313, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.17127810877064262, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.4177685028472229, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.21087258811486068, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.4182975936964002, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.06570335870921905, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.2479447435027854, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.11560620039242474, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.2786890063705584, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.09867858411809763, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.3225529873990059, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.12370218124034608, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.3512013342182375, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.22396412213589117, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4759025637784212, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.15627978895992434, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.32774682416221296, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.22220265603625808, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.3850042924274655, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.23925860034637106, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4322103094292488, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.2340940710746067, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.41823616908031946, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.12790043463054807, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.3251137272879362, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.20381173318192514, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.4374242147608937, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.1863636050757979, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.38327347200836553, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.13774451171759725, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.3392358805928605, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.10995304272182382, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.31516290141130093, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.153929566721589, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.3608257907466213, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.09576088800276077, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.3041295470213464, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.09587088737227797, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.2616214569856814, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.09302909573829315, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.1930745826064226, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.22277635660975664, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.4138180006822518, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.12683453413302323, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.32324923216936663, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.10406813778823464, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.32304117956922, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.11433133814822793, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.376685707847211, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.16566832287055458, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.3899280134984665, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.16279177723066465, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4102368807414641, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.1418972100477343, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.35549463565231143, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.1340739087751559, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.29651992518206227, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.11739016262053983, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.3243598686623998, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.12391818909971714, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.35690404186806807, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.1293238011288526, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.4229943657542825, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.03625427565378279, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.07306837018670909, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.39671144662530883, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.160940602711541, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.42923242729167044, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.04819270896239086, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.262682816076646, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.11764942628273296, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.3661118918972216, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.1546502365264458, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.37662498358584207, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.16053664506786586, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.05360431433749398, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.21840614866685698, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.146687038685289, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.10180668728147267, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3387919511268085, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.15878190990009447, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4717304128091511, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.165417615101112, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3723049467309275, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.14493605424503186, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.3501358359880476, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.1270407903803617, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.3551178453495837, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.08711637171502758, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.2954967025562741, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.1502843121431226, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.390370937242866, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.2089790450123036, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.5020912846079854, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.1224795031512657, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.29049145213151384, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.08810199114550488, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.25421876554719885, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.1723666822203382, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.4164179694728134, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.08174592824469444, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.28125186470074287, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.10716023124329743, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.33305109264677923, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.16831858516266504, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.44925788158953217, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.06005500834321576, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.23500168157276313, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.09532344847561978, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.27911273015721655, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.1620442038279161, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.44671116906860114, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.0808656459604844, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.31629942918298065, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.10362141065231315, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.2976713869608838, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0535442755496515, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.32534949147415587, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.10502639606076236, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3443858948320673, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.20843904443769717, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.41987041749209575, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.16892311117272107, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.42944637897474097, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.09407649401384535, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.24845011725491462, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.08853913752009362, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.3699120467510799, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.10565962599924915, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.3576984412786932, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.07750873793282746, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.42519667805364314, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.07351837954322755, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.16306869473764823, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.09530685695259108, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.324860923353352, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.06261022269185519, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.16543452283536295, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.10417702105111015, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.2840081496768262, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.22195513186933313, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.41825817264037385, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.10512531898680018, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3280524648390448, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.06549365852999947, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.19948256778755252, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.33171820256493456, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.5317418755857823, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.13801294746633136, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3369282304053488, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.05045310628409221, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.26506847806653416, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.1177915530693848, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.44418786085508993, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.146547094309055, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.36840754531694414, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.055310713185595, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.25742908684385607, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.20576246677399845, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.3789603596807018, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.07528967210822063, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.2659777826374339, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.17509809383946048, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.386834770913833, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.16322400014183205, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.47216572692709596, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.13050295514132168, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.37331190108047335, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.05116952807627418, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.10314036721569257, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.24963395554422432, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.043321633865040066, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.1541835268049213, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.13410301071131794, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.3942932268034351, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.598931508663349, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.7353063745802827, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.30677064886592076, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.5308555945242818, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.17328174803055044, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.3178268797869574, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.4262221594184117, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.5886657414856064, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.286608441075188, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.4579283646292802, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.3315037521841549, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.468197879470805, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.43186481103649477, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5792139686527714, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.30890092021323623, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.5553909583113487, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.22218130727359342, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.39929356245904674, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.46092611919700416, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.6365915338629015, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.1690979933029136, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.3751861276375209, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.26538706048179084, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.4982627378595717, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.5234484809182233, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.6658297773613274, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.2840563956846642, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.5110250591004448, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.15161074985415177, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.3796830006266126, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.3815250264738168, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.6516314751979607, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.19920413481788912, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.42537796926163113, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.18679710353734788, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3876457319870774, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.40003810431098236, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5899097408105687, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.20401796878756984, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.43317630453631556, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.21812881407613688, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3598346059855135, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.38047531731529327, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.49485723102957346, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.2044887070217883, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.38471585132587544, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.24586918158076287, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.4658595745396681, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.4489235959690452, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.5934678825154104, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.2980504190448601, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.5101268920225042, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.46832763312452297, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.8176110134774669, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.9436043261706615, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.9880191679951993, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.21039673882735752, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.3872019296036794, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.3642482472579296, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.5342538783335161, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.18831933500600306, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.4318025704181776, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.3395693620772222, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.28406136898728457, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5649283064490618, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.21544027588567594, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5040038440508637, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.22556860731509948, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4747086049005634, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.23843418577408987, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.4082320855803597, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.26970223719007375, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.5172978597562362, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.25449674462950855, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.44805409822643144, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.49458876622696707, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.6179893617801274, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.30630098078522544, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.5439056051092116, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.3312570339636223, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.45442661484375735, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.41520313827696, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.6485212540886613, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.19850842371858787, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.43584341835040474, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.22744906705116497, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.37233302529431345, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.5112697990822607, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.20170335119323748, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.3541251997977811, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.16542259679471108, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.26975832150444645, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3857901147929391, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4926358895461277, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.10508106635796587, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3182774828667731, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.2831988281847858, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.16885023000999705, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3897135623573608, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.2309552734743087, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.43975656978777905, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.21877512875558908, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.46843499948065653, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.3325026294099889, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.45805631044287126, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.23530033724858213, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.46208607300298377, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.1759696284842668, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.40989005404786566, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.4824794737945071, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.6479459161283603, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.37284027455688556, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.5528347504734102, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.14722675403683808, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.28846790344058515, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.4656455050518963, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5477103600632085, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.2887308472548599, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.38846174119508314, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.2542828011834812, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4695941026465371, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.485644095022506, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.5923993450097689, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.15487293534817623, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.39293494862736383, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.19659284558894802, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.3439604955527307, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.3150760288937462, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.4551575101683354, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.21741853044139284, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.3535910166292039, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.5046613014990851, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.6377969619576389, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.6485902560215636, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.7627201392474565, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.33626819961829335, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.5466581859383387, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.20326213373677707, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.4211311971791892, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.38713346831820944, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.5376493568188783, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.32000331642122953, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.5480591855923784, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.12890680068769322, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.2478022357548686, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.49124012500448727, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.21132630077912357, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.4175670766052166, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.14440270272056518, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3829771215415724, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.5543498698280007, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.7016802877815009, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.13108369255325433, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3929302741911199, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1667112120846934, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.30913125513655043, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.13203823352287472, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.28280767234695003, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.20174045447955946, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.33729298835089516, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.20455275179869584, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.47815735761186096, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.37420316460821246, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.6481907872475802, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.10878661088699644, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.4101850467281004, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.2280725846401638, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.32365707034585395, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4584149294578286, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.13894362470892055, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.35710461878741834, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.18945235333331134, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.3443950901432381, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.26637160423927314, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.4646735366228476, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.19585063466021865, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.37259242197674974, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.1581734375963556, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.29855796123914957, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.41749084544527715, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.5512835123193889, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.2661644792674617, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.46546633658762687, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.16832254701348195, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.34172735320777375, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.39245477087067665, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.5302932215753233, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.17171159782066198, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4250539223489113, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.1567864814929981, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.29896910170538116, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.41423657620328247, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.1524830877429947, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.4102495208939548, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.6896260480312464, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.47475604110292025, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.6309823582859546, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.2685172542195998, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.5385038880406502, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.23511486401816076, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.4879376273715227, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.46676620029268096, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.5960578086281888, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.21011665246752942, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.5022122132107005, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.23892317781280908, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.38939729384213495, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.3481041677117235, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.5683248500873576, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.2931120472907597, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.5551374467086605, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0935071820875984, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.3104146584296793, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.46742290550462806, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.6201011845566285, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.312650266868888, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.127245399039237, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.08385867792924734, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.1131435241082435, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.3955646912745367, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.5363251034746059, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.26460159523593296, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.4803700055675181, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.12561164303321054, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.47038542160135094, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.12748893606628386, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3557730263992019, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.4174381195316011, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.5467874115748124, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.18187597339521155, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.47371700399657607, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.18399961762411743, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.24762685010055863, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.380770036603192, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.2372622545962587, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.41017604192890195, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.15798724534926178, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.09458362068147118, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.19112709920459806, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.26917712505386043, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.11450137919698138, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.38588319985262204, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.2529258575884984, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.43636064973584276, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.2206598690689583, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.4671100153557676, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.3284807347106534, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.19276506991327308, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.43458455506290555, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.28127656729267564, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.48992770341073005, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.2584188371476316, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.37301467093894103, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.4094746713677566, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.5127629442173787, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.1978740176644931, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.3475150762120378, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.12525435825547931, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2209612814301191, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.11872519045542135, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.1415901806866318, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.12467595443249284, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.2225814067024197, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.1386200663966604, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.1507724411705623, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3882065230979266, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5170531810333934, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.27850162207652013, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4893867900242687, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.2686424829558855, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3998516011592878, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.7037873295747725, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.7990268043083656, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.36484904083194636, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.5860311918255953, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.14220602298368126, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.39434634170155597, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.17627564495170006, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.2829970218265084, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.1526113403954924, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.24044159635524803, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4467052322987113, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.4269094075482239, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.6440338986542221, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.2089934379295256, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4202179280810887, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.23927776234174902, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.42492275577244626, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.4192565023565104, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.47988160867636526, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.2825074232826454, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4576805072760733, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.24073557586211028, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.42665885117139607, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.37356506757316704, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.5184539879286838, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.26105773506180324, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.4938667045198544, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.29977450507928116, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.33448899741633614, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.4659921217718883, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.08369850049073722, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.2901642042976994, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.15901023657267704, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.08048862002869049, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.1853605878762701, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.14911046740590622, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.31528213773035774, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.19951297936500814, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.3268993135281582, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.17837945138789355, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.23465398368701498, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.45367638954943146, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.19472361650315084, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.40377628308461305, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.36966653028794927, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.619000557599158, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.14978817967886865, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3579627976703376, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.3428955163829333, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4549331138881434, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.19374128629783371, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.42300747804792893, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.19196608410425278, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.4492698041709823, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.529528271776728, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.1768429537093963, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.39729894405642474, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.1783827232160263, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.420993901006138, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.5471998982127312, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.7261143787285806, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.28098066731217336, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.5947928282659879, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.3471867713780383, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.43403373030619585, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.33731180652769377, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.43284789974371823, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.25107542027773755, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.4717531424710489, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.12765417324195955, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.10215316399947212, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.11108510046198607, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.22669018884314224, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.44041899547143254, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1701094120440135, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.29286151337006916, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.2927933973558131, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.47375496223846336, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.06874614919231697, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.20986932076566409, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.1441116002025322, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.23046678878134805, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.18415822638260726, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4239216335535842, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.2916607130801699, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.530090321409246, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.5344974294085829, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.6840734337993466, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.24006100607956476, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.525627718929817, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3180137236294719, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.485644095022506, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.5954238368250169, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.3762634236591465, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.33384668064796064, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4509736001471859, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.27392978689521524, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.4257914116040595, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.17712030567063494, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3607125350126197, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.20135763034646928, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.35006080282921004, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.37565846334638286, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.45365001576190844, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.25087428990920285, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.4056641749589937, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.1529665009156386, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.15471428129658021, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.23308330456083767, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.19252575667755267, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.18545347920261077, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.3552926519343793, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5830807494515953, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.2440425026082214, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4841963273421365, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.12514106545496687, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.07142565875275515, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.156820371591221, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.34038446123808824, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.5113782796801761, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.1423117641326302, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.09621288561909111, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.19434864892148712, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.15449597020263703, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.006107696271654331, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.38082873348976415, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5493718467604206, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.36481383830535447, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.5676950665117104, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.19951297936500814, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.30595434646385716, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.3491726680217181, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.49174493737704345, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.20326213373677707, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3965155400704921, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.14220836651767108, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.19783691883509516, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.35420217205091864, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.14287380394182542, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.14713433937849357, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.23515811334479123, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.41733625901113247, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.2550611509722341, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.36821398145189993, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.6015510626637584, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.22008558571360354, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.4407629091157834, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.4292296939530436, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.1349922772392652, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.1381958549483014, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.26422743815167654, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.11714319535206957, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.20972571494011877, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.395894071208527, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.18559542135951204, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.3804842882867387, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_from", - "metric": "chrf", - "score": 0.35369375385786006, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.12475846123062707, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.27823340731817514, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.15122189206102096, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.26750110507308866, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "bleu", - "score": 0.10759927692349745, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_from", - "metric": "chrf", - "score": 0.21065794536310511, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.30327872414714485, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.49804213541579834, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.21685485833927476, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.3714219747170047, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "bleu", - "score": 0.12274092982883021, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_from", - "metric": "chrf", - "score": 0.3385513651938691, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.12787395553510186, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.33752742535974617, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.112289032173749, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.17726100052085036, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_from", - "metric": "chrf", - "score": 0.31017716089889963, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.39962545473912425, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.3710595252626966, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "bleu", - "score": 0.21688283061839067, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_from", - "metric": "chrf", - "score": 0.41775824162589076, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.14326513489612383, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.4034278533385552, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.12666372160329223, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.2650373529479294, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "bleu", - "score": 0.12162779391619735, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_from", - "metric": "chrf", - "score": 0.3228288840559658, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.18294117097472648, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4383387744769579, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.203264842568494, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.2922087191170089, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "bleu", - "score": 0.18237599479708327, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3740403511567824, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.20298407172594946, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.427376330935813, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.1740044679403827, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.36375152376157177, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "bleu", - "score": 0.12876689524369925, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3253153379449275, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.15626231814206226, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.2918712789926548, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.322788951728102, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.40263021320001785, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "bleu", - "score": 0.119159749312327, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_from", - "metric": "chrf", - "score": 0.21297942664093145, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.21397099133614067, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3568171392601981, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.16925466459550803, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.35912398848424326, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "bleu", - "score": 0.2036348471340078, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3472831655579266, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.2298971389591186, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.45764667682340326, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.2327080490816513, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.4213315211213489, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_from", - "metric": "chrf", - "score": 0.24362353508932386, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.2769725060346048, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.2568191876426829, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_from", - "metric": "chrf", - "score": 0.28135849152758385, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.3238973846683935, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.12832055613623328, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.19433944404681203, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "bleu", - "score": 0.14482189302397735, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_from", - "metric": "chrf", - "score": 0.2913876815877049, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.37693028676849333, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.14410670132605607, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.24025207593480963, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_from", - "metric": "chrf", - "score": 0.16306957103469613, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.24942094354139677, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.9199349282509897, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_from", - "metric": "chrf", - "score": 0.9199349282509897, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.21688283061839067, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.4479129164961325, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.27434065146872866, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.4551761513917315, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_from", - "metric": "chrf", - "score": 0.28112283847231073, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.2112174444529806, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.37115876147810895, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.11460384138378832, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.32308861733051, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "bleu", - "score": 0.1308613527030366, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3063146286877558, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.12030921204016166, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.2935108999290831, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.22974300992320248, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.35766721538849355, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "bleu", - "score": 0.12787395553510186, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_from", - "metric": "chrf", - "score": 0.21931515993565381, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.20236126962624626, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.3258121781111335, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.1812045836887171, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.18649703687001343, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_from", - "metric": "chrf", - "score": 0.1441966459257424, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.23870544239673078, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.30389718661514126, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.14288815197601673, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_from", - "metric": "chrf", - "score": 0.14957316612525498, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.17081061355061614, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3645499017230567, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.26958290276046354, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3771988116643981, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "bleu", - "score": 0.27675048474641756, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3780460244391623, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.3615889761528277, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.2758862937563794, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.4673996585329364, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "bleu", - "score": 0.12503614625842938, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_from", - "metric": "chrf", - "score": 0.20624064341134082, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.20588815727980112, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.41944461991174653, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.28234422994155567, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.40408604199549997, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_from", - "metric": "chrf", - "score": 0.3368893372278425, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.13588969750586194, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.3523239132597748, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.1781853859048144, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.36865727091511874, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_from", - "metric": "chrf", - "score": 0.2961559727627133, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.2775686235755007, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.12416350645592025, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.23265120010755289, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "bleu", - "score": 0.12846497020051437, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_from", - "metric": "chrf", - "score": 0.2670865602673704, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.217554942150074, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.4362387654025806, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.18772266185346026, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.4516796575038181, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "bleu", - "score": 0.28252374116432993, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_from", - "metric": "chrf", - "score": 0.3549531183419122, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.12876689524369925, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3034375834959013, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.10531636385748798, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.15775047351971955, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_from", - "metric": "chrf", - "score": 0.26128489301072644, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.18285404868730815, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.30239028036773985, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1789898550500511, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3097165910502381, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_from", - "metric": "chrf", - "score": 0.2126837065505244, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.23292164090728384, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.4807364086898486, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.15742302643532463, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.3220278551038813, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "bleu", - "score": 0.18889796346849766, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_from", - "metric": "chrf", - "score": 0.390828018955539, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.15404632289830114, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3934040018417114, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.14855426866172083, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.4089031318363594, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "bleu", - "score": 0.1736086198203101, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_from", - "metric": "chrf", - "score": 0.3517982963278223, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.15606652450871636, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.38676973597326414, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.346045680932875, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.4621083930255766, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_from", - "metric": "chrf", - "score": 0.25751650996406256, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.13628770358024436, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.30464291275706445, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.2873180113751827, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.3691291664744644, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_from", - "metric": "chrf", - "score": 0.21636840076404606, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.29331713922012836, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.18582826054135923, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.27931164611946097, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "bleu", - "score": 0.13628770358024436, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_from", - "metric": "chrf", - "score": 0.196045070105177, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.22256474447332572, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.1087256678530004, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.1812150267056357, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_from", - "metric": "chrf", - "score": 0.09624090077172921, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.27274442393032494, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.4767475272675149, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.08206174754800233, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.24600065227133203, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_from", - "metric": "chrf", - "score": 0.2894206730562163, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.32404902054836443, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.13600287923663476, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.296137260965594, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_from", - "metric": "chrf", - "score": 0.29939861106519894, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.2711712970899214, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.12748547320686965, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.2256255768392581, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_from", - "metric": "chrf", - "score": 0.13897785762455162, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.2418791601714353, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.3327258966414523, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.18472476303374016, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.3755456818093384, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_from", - "metric": "chrf", - "score": 0.16879768238484785, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.10028126671358768, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.21465229625864304, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.12004125280185217, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_from", - "metric": "chrf", - "score": 0.13075268692454742, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.16340836420369564, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.36283746947775286, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.2012788513843773, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.3241416301984527, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "bleu", - "score": 0.222140444588514, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_from", - "metric": "chrf", - "score": 0.29953031595565194, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.17092467746295725, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.36754216836174997, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.2290624375320133, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.3703637148185826, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_from", - "metric": "chrf", - "score": 0.20316405901471601, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.2048509043540121, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.30660769477099914, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.13583266175611605, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.3216755467134329, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_from", - "metric": "chrf", - "score": 0.15351923691242442, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.2625069486168988, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.18398732411042557, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.2401204673210609, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_from", - "metric": "chrf", - "score": 0.2557074827472021, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.14645066834461026, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.3063157759715837, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.13937542038981274, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.2484339727687842, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_from", - "metric": "chrf", - "score": 0.2737880982480958, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.4018398428695008, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.13382613080002836, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.2537208483050712, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_from", - "metric": "chrf", - "score": 0.2630950732259493, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.19834633509680927, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.3614699644212251, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.19000532642952978, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.2405617210713385, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "bleu", - "score": 0.13181313433495553, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_from", - "metric": "chrf", - "score": 0.22684236479857312, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.21010332378415866, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.16049139739945859, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_from", - "metric": "chrf", - "score": 0.019878741152560272, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.22559518514805962, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.10902248103931993, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_from", - "metric": "chrf", - "score": 0.16583300501883477, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.2154897801937284, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.4083528236853434, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.1740044679403827, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3783149893116463, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "bleu", - "score": 0.1258273118584677, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3207394929288255, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.16574121720327287, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.3831242265731415, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.25011851152889697, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.37126196571844006, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "bleu", - "score": 0.05671337518059672, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_from", - "metric": "chrf", - "score": 0.26251266297831083, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.10085167559661873, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.18125609699008438, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.07021707359312077, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.22277615768791725, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "bleu", - "score": 0.08568635726825895, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_from", - "metric": "chrf", - "score": 0.15015893458515112, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.2511187197601112, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.47819642315416905, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.3506669990311196, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.5110276476843241, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "bleu", - "score": 0.2823806497463373, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_from", - "metric": "chrf", - "score": 0.4097065111577764, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.1537414828207279, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.3722050787080825, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.20079789489773447, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.36306781014142475, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_from", - "metric": "chrf", - "score": 0.18254530689454584, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.2572390116372129, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.13966768009198655, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_from", - "metric": "chrf", - "score": 0.2813477376997818, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.15014755317658912, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.37836116314741347, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.06225053846006199, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.19628052952282465, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_from", - "metric": "chrf", - "score": 0.2461113033172792, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.13600898159884844, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.3230757564905893, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.2235267829375094, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.4197003930616035, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "bleu", - "score": 0.12017396628208415, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_from", - "metric": "chrf", - "score": 0.17861403940933454, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.13181313433495553, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.28588995835566733, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.1509901905071242, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.42614589006990955, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_from", - "metric": "chrf", - "score": 0.16422774333078005, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.19928950404960785, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.3515916946368607, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.23693055763743093, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.47110207134358734, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "bleu", - "score": 0.12322620396842734, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_from", - "metric": "chrf", - "score": 0.2816556920367689, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.1250305362182298, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.35192066105839037, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.13181313433495553, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.23734991438269704, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_from", - "metric": "chrf", - "score": 0.05708041498286245, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.39208241867588406, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.12671660613804978, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.3813787743264216, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "bleu", - "score": 0.16338968219757316, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_from", - "metric": "chrf", - "score": 0.43516585142042474, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.3141940399992296, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.2175732217739929, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.26934434229495274, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "bleu", - "score": 0.10434360980785336, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_from", - "metric": "chrf", - "score": 0.1965525334564022, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.19331968002780792, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.30653379537681946, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.16419136872156925, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.38578825514877557, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "bleu", - "score": 0.11319316697505612, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_from", - "metric": "chrf", - "score": 0.3044933526278424, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.10372851412328025, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.05428552151774627, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.08170272572786982, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_from", - "metric": "chrf", - "score": 0.054560358307203495, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.2197940423573754, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3252925042873819, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_from", - "metric": "chrf", - "score": 0.2386512909161297, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.16894127989367852, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.3419460050290285, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.3808157877385458, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.4468825428794822, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "bleu", - "score": 0.0810371533925042, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_from", - "metric": "chrf", - "score": 0.14661692946967528, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.14062598436731893, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.3764695982007195, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.26772209592710927, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "bleu", - "score": 0.16587560311800356, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_from", - "metric": "chrf", - "score": 0.36304298665164114, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.19207278754983098, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.18980024752692398, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.17719555918098742, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "bleu", - "score": 0.125919848913809, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_from", - "metric": "chrf", - "score": 0.12820373892360745, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.1968536715007284, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.333542500417417, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.17016486621490087, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.3423671585123332, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_from", - "metric": "chrf", - "score": 0.20172859170422008, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.14976409594561182, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.35357199599186406, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.1665583359843711, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.2627459510960287, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_from", - "metric": "chrf", - "score": 0.26627996704195217, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.20740300708624634, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.11206360906932318, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_from", - "metric": "chrf", - "score": 0.11591282390598331, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.19393790238357375, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "bleu", - "score": 0.11424261736422782, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_from", - "metric": "chrf", - "score": 0.2214641710932888, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.2354734090463839, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.15803708011407422, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_from", - "metric": "chrf", - "score": 0.1534362334139164, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.029484944886992947, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.08447773742536654, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.13534893625087907, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_from", - "metric": "chrf", - "score": 0.09370499064568831, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.41557169141417455, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.2152971203854131, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.45844266102619613, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_from", - "metric": "chrf", - "score": 0.3510795373941694, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.2603954279622387, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.30277029197532107, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.4119930658213665, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_from", - "metric": "chrf", - "score": 0.3172363525732528, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.09824473131578967, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.26161454205511375, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.17813207960290023, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_from", - "metric": "chrf", - "score": 0.12613950642084928, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.1077448900968642, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.1466632434186726, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.19398573687939527, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "bleu", - "score": 0.11116961409150189, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_from", - "metric": "chrf", - "score": 0.14407603400456293, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.1535686541317235, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.3273820311085689, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.1479757676110522, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.36882257747840863, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_from", - "metric": "chrf", - "score": 0.26565870470756586, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.2393868174483411, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.16951713127949472, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_from", - "metric": "chrf", - "score": 0.13967106347277614, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.5745954681260859, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7920051188244848, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.6358921902612438, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.8041899227402122, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.6299285159340671, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7993134129243716, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.3572514590810421, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.40312319760122833, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.35059076445515835, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.40219803477483124, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.41316127706749806, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4430321339435623, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.9878765474230741, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.9958930217841712, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.8780634320789833, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.926946700115022, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.7964573357809173, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.8458636471716781, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.35601247064914876, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6528728847159075, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.40673971192998765, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6897190926100627, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3707525915417785, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6481906761834414, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.5724622291345857, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.6818279156433621, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.703373719677874, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.7784050705257474, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.469958733898233, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.5843756060033074, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.2676232320051144, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5440246804235981, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.3489926819498492, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5715668842319502, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.2786169604662155, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5267252236203236, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3765213224289163, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6469521424555786, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3410244689880313, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5816669416914216, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4234343012313773, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6625289905598352, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.44219732271776674, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6193429426274062, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.4324680011853555, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5877600878871951, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.4493940083619696, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6230960824462234, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.6638859619095425, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.7874224590682172, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.6947677373756656, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.7941300666655116, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.6412098671661826, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.7665040244283648, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4845227999608418, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5968050469845498, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3861375213265022, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5122109329134508, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.32539921259497445, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5133457276293165, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.47269414327373943, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.7451099574206652, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.4354194543126476, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6656175329857803, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.5941815558294462, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.7983203558832153, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.4143449478847806, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6736569430464404, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3983045920261205, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6521777108605036, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.268203877206376, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5791297455379081, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.3720001389308944, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.7013845085492982, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.17329990217896798, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.583781848253705, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.3373556859342653, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6738789170291255, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.4494597917400064, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.7073438158390085, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.4446730260276365, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.755908468739292, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.43478132178539325, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.7018196083546635, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.3268845394941929, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.5177343510524726, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.28038937103419465, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.5038494750471553, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.25718495991757767, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.4369258127692308, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.2598777182656361, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.5891629072611128, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.2989825848955476, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.5979372541912472, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.21832405319137094, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.538599666863523, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.15922876554252086, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.39205452902204047, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2607899218485117, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.48702498962539814, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.19112125497758137, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.39870104995538236, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.1061903685456685, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.48402103757719056, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.16158718602920916, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.529420842984689, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.11815153359326112, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4449148298646824, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.4840168429540741, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.708011141564384, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.4280674425361325, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6762864074630727, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.3476608425783186, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6262956160259413, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.260560100033495, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5367621571346236, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.31513262466552094, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.6088063321214817, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.328480036965797, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5845846160692275, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.34818832435375924, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.6021958119247758, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3357114888560433, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.577627721559994, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.165917178563774, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.47788177649200114, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3962150993148768, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6615791069918547, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2715808911127579, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5912854463960201, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3561131937728394, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6360822051576717, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.30843187897727053, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.3486791970487533, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.30006024473641996, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.3256826624869121, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.20022216695167708, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.25475796453209737, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.23057388791871672, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.28722063151007776, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.20138961649645912, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.31544376598852375, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.18010353259801426, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.2514369893270279, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.3878454500259306, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.6551636735823242, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.3575554083195387, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.6357905858551194, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.38341396472331346, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.6437362313865919, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.36350084013796624, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6256665663158201, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.3212586102862301, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6200344079713044, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.29542603524950894, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6045890208480269, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.31094933095062055, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.49068855707946196, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.26045893297751727, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4556002624646449, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.25769536520621106, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4479264653484257, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.3833596037687312, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6303767331020778, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.33202003790347423, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6008057921287521, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.5169325988486032, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.7139612818852349, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.5350553356274835, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.6061404961531679, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.48468513699279653, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.627759796330558, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.30044261567697145, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.5072959120235889, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.16111837221606704, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3897870969473364, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.10167233309625472, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3890033983715864, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3452100271202966, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.29945813065831656, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.5652964318283186, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.3118864893794733, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.6025015600895789, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.4136053909671976, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.6322647535881054, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.2170322997863664, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.5313522319806132, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.26361261152036314, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.5725817956180734, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.1678792928110798, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.5011442124633559, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.40476128586074045, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5819090999793647, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.31924314606108933, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5643587039540041, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.46465436703612695, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6187472056628097, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.23765992259974003, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.555280304898008, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.14222805709331154, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4996646755261327, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.19867232982300087, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4721193400035613, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.3540078976511945, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.5545213530835353, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.30065550001026614, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.5078021900511434, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.2861877593848395, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.497612333201281, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.26031375400822604, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.6435901265581367, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.28663599743133195, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.6523798359183501, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.26536873046244686, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.6087318332086314, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.16720443618568337, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.49728602865615185, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.2237271965508778, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.5188036228566616, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.1758067209813282, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.4901843428646942, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.11927023953333708, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.30235008020722276, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.23340024365107623, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.3615501139102133, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.05099372834862051, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.19652888728631965, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.1552412395318371, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.46901193090489374, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3628388824307182, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3074263382421554, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.33472487399064255, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.5323967201407147, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.2873736840134788, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.5010578596526507, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.23664302078708985, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.4547035743969898, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.2262279556088844, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5760442354634835, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.2531889405970385, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.6038946560162178, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.21931836015563075, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5700300210408424, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.24134481763339574, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.5039460152723452, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.2348279301335576, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.5004871814463647, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.08237331643927553, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.39243470995755453, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.2142336001450868, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.5588585581750418, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.09648154986811164, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.445584066700863, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.18089468280268076, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.5010395255727423, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3101522533089342, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.604637604976383, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.38075337128063264, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6303731272422745, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.31147021123578866, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5943977261450569, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.3167263933365905, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.5418529871586636, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.22655843030546713, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.4345585649515925, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.3568884258190913, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.554204547339302, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.3954105975011071, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.665702837892058, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.31671795070859093, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5824028981642948, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2891201026404864, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.577907772782264, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1440960867359316, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.317244026262994, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.09722244673293699, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.27113802032744583, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.13367647104732472, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.051791256473099075, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.365621155540599, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.3315860669681651, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.04012260068601062, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.2696128056189901, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.33711190260900914, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5734011889114915, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.5580417299024397, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.6857939145706653, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.18742174533907147, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5476333057836739, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.23173637276917056, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4688999062248428, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.15237690319868696, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4251100485788087, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.21347502421469977, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.45172058784807567, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.23160979893862282, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.5307682448377248, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.14917391092771218, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.5422937768900143, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.3800143437750757, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.4541968077704817, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6895568152401309, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.5714674895346293, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.7513731235157427, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.5133263413524151, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.7211829449070788, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.35051963517598583, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5957877277673226, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.3574343577949326, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.6497698769139355, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.40103978472952795, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.6208328012476202, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.08894652425495941, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.41017528256257657, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.22464540307431463, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.5478473333306936, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.12081705083061788, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.42330662612715014, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.10809027944114537, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.41709635067440054, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.24967258145788696, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.2221215858584901, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.14721095611762033, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.5659463345055759, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3833384649248694, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3068895477125971, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.10421454499099432, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.4482718797876954, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.09809739305025474, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.43620207901811114, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.06617762054068453, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.37651507936877043, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.30512514107707417, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.5253825791967487, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.29026498240122633, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.5281110282763906, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.21608519654486127, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.48049705425952316, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.1976518550814801, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5244055159079589, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.26410908345664563, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5677920940498072, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2588340456184726, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.55968436904969, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.3004098099879873, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.47263075055005355, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.357133009467308, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.5076629572579336, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.3317061376682229, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.49116761313547225, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.07426303717403786, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.32419436785022854, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.32990225159044795, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.5675673358712833, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.10176396205307862, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.32135019548795624, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.311511414478067, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.6033227598801263, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.22779349070551677, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.49148253463628344, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.22115130993130303, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5521258614574281, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.20542693687806493, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.07296118741828052, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.2422245788581219, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.09504015903132065, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4293817955338464, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.15438932814303225, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4752857803786606, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3324917175608352, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.40473260822223667, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.7095471138795382, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2952023404990282, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5787510650657961, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.27191061976527564, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5817893211228, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.417977745559327, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6309214915513178, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.37902282569315715, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6372123873874835, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.2635271766530794, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6035397157843727, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.4064316590586192, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6473114303275844, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.2855640284366791, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5870028589262669, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.3535072546729628, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6067505948373164, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.5169107752364505, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6794853149665443, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.5353289105105035, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.7178935320712556, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.5510544576491839, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6898993575925141, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.30587159272611075, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.4856692118018501, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.3739787291921192, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5302315354733708, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.03630887444624427, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.18449043718721744, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4324660136998897, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.444143437866834, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.28337457669614124, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.11457550862274267, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4234525365021209, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.11506534027158988, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.45183832289757403, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.07653930552226329, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3454416722587219, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.15141938460939539, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.547291242951542, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.06453967836796516, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.4154818199721149, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.2933101487116941, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.26075278487602266, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.303183815224326, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.20679375298337374, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.3076750746495824, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.46542265321304765, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2317209329773014, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.43185448543679017, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2909986146455974, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.47042977301741506, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.25506473041366917, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.5698114406236083, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.20175458741739072, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.5445587371263559, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.2575855673150857, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.5493846271661655, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.07272528883632293, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.404446825928217, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.1337989438650252, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.5813867224396951, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.08617288043560194, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3776558917820924, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.07938718996384923, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.18817142418518176, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.07201542184499009, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.24935341247163162, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.09121255946496629, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.23409194618638485, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.20019796122672592, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.4810502579226327, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.2517564097762976, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.5081933712560073, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.20149292377213346, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.46775181788199904, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2955812558020175, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2401592192636423, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.09019417034682699, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.28822910320599077, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.6087031937056202, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.3880515884750121, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.6587916715823183, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.5142726846179982, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7344716263345912, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.4094748015187699, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4288513205758089, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.4487746167679644, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4476730201191672, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.2836623400057614, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.29147337237183046, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.16950698451288215, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.48668984177868246, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.2113054108348111, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.44238229987470284, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.26207903587847736, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.50073123223194, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.4527112325797497, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6708989870027865, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.4556160153884204, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6661994452325181, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3216756020053242, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6141241026166391, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.3977038258772401, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.6202897864314184, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.37570809340937233, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.6339141734561076, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.559332422592187, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.733291190094771, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.3167585643537871, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5076869840147092, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.3446592076818278, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5819912583909785, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.23270938096152352, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.4490269267329941, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.44114781827798216, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6241365710582877, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.529527758323629, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6540432510655854, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.49704232910799745, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6453248294274054, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3542266508664836, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5643413028542406, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3479698393875884, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5760833125751785, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.24373253714463095, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.49482039214573803, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.3995439803178399, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6021193793256325, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.2988697040013311, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.5442522660489195, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.500703635659656, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6501904887399698, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.2993081268625724, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.47777429598730525, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.43330223254789785, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5564499529933307, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.1466607445607986, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.36552963821230766, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.35312894221988256, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.5483853808672988, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.41807822202441103, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.577545891208518, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.3475258894340562, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.5729813197277963, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3473313422920779, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6495220842154038, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.20238796310390209, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5665467522687606, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.4612469192468151, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.689540484203802, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.3319181496626261, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6296213700542458, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.45718638941364104, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6765316874457515, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.2842437601270078, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.616554183160495, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.5145500336945869, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.6710712793486331, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.6260866791475674, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.7122695616091047, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.3856140451435003, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5942230347389459, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.29427156769985635, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.38674923884011136, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.025127088788317715, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.21031980892802613, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.14721260533033206, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.2721389124032325, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4224062856802975, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.23333094197299464, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.49932033002402926, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.11159818222678333, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4729286927154353, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3095017641836787, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5048955319030237, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4060492501139825, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5683580956250115, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.24406315755131383, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.4895502947549771, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.3534880761230573, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.631198012145244, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.07640690432316208, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4641021856152639, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.16305626357596484, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4931017709619054, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.1806974226541495, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.4264281995893693, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5686715593689737, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.3755133068349505, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5350958966397039, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.23876161112129105, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5060111681210002, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.48773160239847224, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.6806798635651312, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.30528565543580843, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5318320483880432, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.33552713250034905, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5622995574132048, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.09056338921321325, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.35831291876413535, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5383434353225599, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.29353984288388507, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.695138133719427, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.36925904697255574, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.7332676622154629, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.22701436815032078, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6596565788920288, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.1552450511464302, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.18842393723950338, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.242345930892648, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.14033475286594138, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.2185459072776493, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.21966878190344116, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.28531911189599546, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.21475571940851748, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.23332152661609917, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.19089930432372385, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.25962807098290386, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.19068201647342703, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.47264292072872943, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.24780611716850762, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.47134154774689047, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.22071227044983457, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.45625358803874827, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.3786316249953693, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6635410443202763, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.37051721129462284, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6498104569938186, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2580007063666063, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.5822544210906975, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3384715911287291, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5853748388768727, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.10361823626504964, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4310581309821413, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.2230178035253426, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5101738085806462, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.09986058288520257, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.36871570224848776, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.36794933674561564, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5158310722885024, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.11504003871888992, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.34098902843025203, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.36601964108639373, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.5845337385286451, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.40551649928110445, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.5930648846584049, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.26393609309752497, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.537555561645112, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.08722778492512923, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3364641574903517, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.17929000882953408, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4496535426738611, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.16236014331815277, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.48989515178016146, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.07838231858034365, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.3561023397717499, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.12507294238386796, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.4138228238855707, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.09662080155533485, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.4004063786929589, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.30952716928360685, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.31930298094188314, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.18843423878971213, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.406619208342576, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.37246426676247424, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5209584150532849, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.28599643357892673, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5040359554493156, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.31290644634463044, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.48183974715675615, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.15984232622995367, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.47596521065582126, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.19598591795373435, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4825413460017427, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.09490574585599613, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.38652552310013205, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.1536201950485081, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.39433169171016624, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.3033134628026753, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.4755698162289715, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.012770470304307417, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.107571889368401, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.46712834333557585, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.7756124961868583, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.5425073523683781, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.7380948085432402, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.5566924420805306, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.7485245832644088, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.10455448325640569, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.4452517051823117, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.15987934837604795, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.5371445877689911, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.20700927851455897, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.5234104249604495, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.04898848695928882, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.05938702344685413, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.2356799309939399, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.11733391315716854, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3665401854549857, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3323242589046854, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3011326009425157, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.07363400452542229, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.3008582090976646, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.08713070321109329, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.26495668798540345, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.10709296666230438, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.27051785140882895, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3564265023508987, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5720558552741405, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3168766888730919, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5556993363671432, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.1914056871173395, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.49658804680546015, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.20777820949105405, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.49320753055615735, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.17261709633699074, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.4066847602885835, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.17293669227382233, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.43566853469949024, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.46356345415255434, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.45763199706851787, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.4006866238149517, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3874784036355021, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6440087418049909, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3524104819165935, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6432066906973225, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.33071760819179763, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5886340872220965, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.2115421630907294, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.4592142318550694, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.1548358410564168, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.47381156956039844, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.41566998270167405, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.20100993861167848, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.42816528421673367, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.36530627395229537, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5407875609358465, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.3452240924044895, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5535093309459415, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.15816202023379808, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.06694383876384004, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.33483358842355604, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.15027544246364394, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.11978799774523341, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.35375346332533086, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.13288189621656632, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.39376971391564713, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.08351204957008757, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.3438749143478485, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.42093878874048907, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.6473313168878321, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.300766546028367, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5375347099200066, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2429883753005781, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5500942714401033, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.2320571360424813, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4518734332878898, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.08435153871730829, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3396241652752055, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3130397888371956, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.19162170741554893, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.529718220134276, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.19063852279381985, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.527809866102274, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.06761844202436226, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.4092757662956698, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.37155720204823606, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6006421195875694, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.42409393275664153, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.624222744304739, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.4429497126432637, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6440718307281338, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.5136648298299584, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.6450420560705616, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.46099008584959905, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.6373572880701773, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.24825115391503105, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4714738437514274, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.3582964458954854, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.10909451748857432, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.37515093102901353, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.3268810409004551, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.09295079562321831, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.34229046446273115, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.28655904581184494, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.4725508462620691, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0747524183542725, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.24565798005663728, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.41678582570423633, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.08897307561927967, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3561293213533616, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.29668241011022123, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.07592692216583019, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.330799461944069, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.08036783502153183, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.4246277236041624, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.06078826337706973, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.3140221984691054, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.21838690739485656, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.44195361269760747, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.1806817845840967, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.4245252650125705, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.08946803054115307, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.3915771574810612, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4801015157149487, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6272559830443027, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.5121292781944586, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6535353826694096, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2762600514536916, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5268462708447845, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.14338573762564966, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.3531021816263784, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.2086384272947034, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.41111566649227, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.15332513333273987, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.2932376272598407, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.04594302966654298, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.24680538829271628, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.2706849406099641, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.2711396488064229, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.45696598587083365, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.287111534154844, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.2951873860944009, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.045411074399305515, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.19534610772698124, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.07220969642779033, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.12878480872416886, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4656205040544615, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.28519788815271513, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5802455455360611, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.35768733769481764, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.28338350923662375, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.49566471724911376, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.29213605340001886, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5193184356046634, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.138833231672613, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.47061483468926485, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.36725466212785407, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.5378300699928413, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.4826464770670779, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6103311193264034, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.3226429253246242, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.4558280044517862, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.4124513407273539, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6927292478929317, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.4270577041161737, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6772877372145952, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.46750299425177155, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6912570546054524, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.47239214217316433, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6826781717152027, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.4380189650991404, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6285301422522439, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.2858251502733532, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5313749753656399, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.4854148148590684, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5985163152295152, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.5647041916493775, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.6502234807392684, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.35839174689995523, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5156712685166046, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.09949076703115871, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.1658343254577952, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5368289150607153, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.2137951235585419, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.31565930043784707, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2564152992831025, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5734154889930266, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.06367523345131179, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.40417603881741776, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3088457262825233, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.554610859906414, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.11823377429398636, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.4865071573440099, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.362911439724043, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.05179532920145171, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.252263377361689, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.23397944996002637, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.909878624371155, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.9494599978334789, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.6484538568755306, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.8387015535622947, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.9625248317849852, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.9799603794887166, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.18690562063516822, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.4977106916309785, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1339727584572257, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.5319216512574707, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.07251137791160432, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.4703241600605098, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.08404094012985504, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4372015242865747, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.14636085397535975, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4526469182638613, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3296972886859299, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.06321303909933033, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.14252585230727824, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.09976480990835405, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.12457006790652007, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.3654990157692545, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.2128456505982782, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.43481131669667605, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.1478211228617202, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.40026283527466844, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.1978878664885206, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2571422518248478, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.14611434422750874, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.6837528314895732, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7968789890147058, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.7017829861193574, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7743327021667388, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.6961795371760597, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7859480663394858, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.2360941227140328, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.35939098278145853, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.14118350058219528, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.20431837779877604, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.1811004938014804, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.2649993136544717, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.23649053182388327, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.4127382174759535, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.20721924345714232, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.36475932190367044, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.11386607947762988, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.33564583347921473, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.570135897056151, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6801332690579707, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.46442643702863534, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5519480629125156, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.6268941789647348, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6958291103494518, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.21305368975019265, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.4371748197696026, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.22837680015088951, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.44164180234500505, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.4151474543103342, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.638952468710771, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.20876900081884944, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.3981381071356935, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.11634129390828839, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.31530902302000635, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.19544795798162903, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.3835451743665027, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.37917766663411384, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5365794450039074, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.359355103997122, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5589602235417395, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4267520229161, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5518115366540288, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3221305290185444, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4866081657424789, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.35551034193127495, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5627284645723449, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.5039752490702457, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.613669501327356, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.6260375038358343, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.7803415401430737, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.5088535943352446, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.625202596789752, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.562048819850726, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.7192054483864224, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3146726146646545, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4709531555683, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3941975148525721, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5191046479503385, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.262633940062176, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.41923206553744197, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.44898438516407524, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6143783254714975, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.2618161850312308, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.46946589430056646, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.4395347891601966, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6124294442602769, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.4850978822371748, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6352541213631081, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.13139413594401378, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.2490406851204271, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3112317271723676, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.4361597730424806, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.49612267717096975, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6218353723304708, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.39997687282627975, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5906362815628093, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.5208833700498166, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6368157603637512, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.3501847839621347, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5180344374850399, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.1743988338080954, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.4684683280769817, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.3335763231736967, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.4822714438205533, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.41618377742781326, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.5456804815374756, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.30485765641951534, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.4770499606054267, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.33469420519942356, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.40802446160905737, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.2719326877457978, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4943569700727416, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.249036269104499, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.42116420214640826, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.46916497710648375, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.6210364770630794, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.1513162576311821, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.3665181321185458, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.17361047672608262, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.39377589303767235, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.12646071698454284, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.35399465579414496, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.7096224667917136, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.8862932371217843, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.5294442646627652, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.7281375072835307, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.933651069586263, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.9586507529693243, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.5425651337252639, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6573851660329229, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.49475425785336474, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5906548177852229, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.509958011324736, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6038542862803142, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.18467608126336754, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.46127619811207604, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.29458137881791246, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5492390632020873, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.154638418688186, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.38427876360308916, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.1379310072046867, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.32409635064062775, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3067124925928069, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4473439946126318, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.2822493397640795, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.46507913833761805, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3925406773051543, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5373872822631721, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2753456537058715, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.4157637470934354, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3360301095319906, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5015691430360719, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.11502119605241674, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.2826072681332473, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.1138894686892089, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.23532055968260987, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.08049386277412464, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.21735060795559732, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.26005633892051505, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.32347988292946617, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.23882935646817824, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.31980378769803924, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.322315347128407, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.38629355287842254, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.21675506796946695, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.44636018244046766, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.23183307484609084, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.4860771998642055, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.291308139574652, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.47517712618294367, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.3011454888332037, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.4262131523304905, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.35933410857228176, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.48586232132101626, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2697896652026255, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.3998510332125744, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.22269084768108507, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4278034123121377, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.1300236096509615, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.32525153283102953, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.29431947865853453, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.44837466661278663, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.07998273930895511, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.2553179648394861, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.10154990983620787, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3241234761287709, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.07911223895726585, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3284566286505505, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.3273734953951328, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.47406821010356615, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.2875779877950604, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.40209911650829044, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.3288944381277255, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.44408070821988965, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.20100292863011363, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4076276304952943, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.28997498044330217, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.49213353233430807, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.14097078788452733, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4079828299257035, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.1548512533490527, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.316352437998455, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.23102354810546433, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.4512153003070141, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.24080045866228475, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.10763639119133948, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.2286324938333245, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.1387209968695978, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.3380551337195283, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.13529314038135454, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.22343406175513267, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3366798594244885, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5032290575942354, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3079971615386303, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.4820111161799533, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.28695849032593473, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.4998009181545032, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.29614367235735506, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.6045301048147214, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.3264083012851069, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.46032850662611646, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.2593432509712634, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4745626718142974, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.3199269653277632, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.46348573637808615, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.0832791679921855, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.2503889973495181, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.20368338136177952, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.3653296593218242, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.4424338955424085, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.6339970261152106, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.4265158106561096, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.5640263785205409, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.4265158106561096, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.5834883274592383, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.14115180190142887, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.3611264285108106, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.17537321780820925, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.43171109126508717, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.05304430074030856, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.2709892265354633, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.18720945362012015, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.2715804874226587, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.12356615100322026, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.2302608543673073, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0685054000547153, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.14139517208631328, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.20881279882974757, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.4043187259329016, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.11473815526787112, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.36686611148406256, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.10400249861669406, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.24794428614874814, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.06306929577938719, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.1592769733360586, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.13977970684956492, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.4014800837643581, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.03947461188342995, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.14847528747028665, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.20045686131572826, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.40666590434690014, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.20748116469976316, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4063660475668118, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.19221269303152164, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.39590642425729394, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.2537557009568589, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.39325950430752504, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.28840308930540803, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.3915762897108857, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.2494491272843294, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.3095153437956992, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.22808349744044165, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.5219559548268804, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.25740737310782613, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.5296577800002638, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.17467275747732053, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.4425746537169907, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.39105282175830797, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5918209407860066, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.20798473392141248, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.4882728259348431, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.38994162074103633, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5563550526031608, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.26949792178164744, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.4573532520066626, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.19154073663245894, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.36853748147123533, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.1561669836509596, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.35203414979696007, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.3367828743677757, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5208619367149742, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.293957196620502, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4618648817849918, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.5370274094269881, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.7083576830089957, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.09559579550755593, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.22721030607923384, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1620171923846691, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.40132306100670667, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.10695860479627832, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.23093180806683553, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.2006816977738918, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.3778907443846581, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.2365826957720282, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.40015265544052253, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.19927817813049292, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.3799201142133713, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.30107111173332013, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.49518939388085714, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.360791478420284, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5455769471781564, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.262924194880141, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.42500595618199777, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.08431948785504675, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3346001936389817, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.12018438120605004, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.41073371100714057, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.05815951947143174, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.25465334407321377, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.38141042305440287, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.6050551830651282, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.23972932680765302, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.45641440058943905, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.1753423380032761, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.3860867724140123, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.3727176326636912, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5936665893096997, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.2883922922854595, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5189711161059738, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.2904236353297477, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5110246787073157, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.1109746392358308, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.3361655324870268, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.21126480857843466, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5208171960282157, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.08514622725334697, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.32324062436989165, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0923710591915157, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.3515127205889234, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.27333560530341, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.2700537967608886, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.05369620163577867, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.17786551143318782, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.2714062063125971, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.06216795401336647, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.24520849281921142, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.20170324785987873, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.41777877902092536, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.14128339612076699, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.31208948933714575, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.14488582350016033, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.28091550902615625, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.3738496420930624, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.6102099909532881, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.30510387810107376, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.5275904051812422, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.2512077334912375, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.42501440166045495, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.20037263749423856, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.4116722318656521, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.12120981066263758, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.28837260181822605, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.0973834065412635, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.3349744739632232, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3307802307098964, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5254270621404842, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.27791708125521297, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.47469089541729687, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.273867164036603, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.4374075951791586, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.2976799101963322, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.444010953670269, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.29096032128390625, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.4378899812097463, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.25430748318960106, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.39529487649625655, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.1518385401250995, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.33666656185298044, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.39332576103648914, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.5905291357670327, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.22403997563360165, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.4163466494058026, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.17289005672834318, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.3272275987435471, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.2722541020028712, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.1578223852154551, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.2505825632099063, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.18062196015850054, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.28314745233130384, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.15698648794278228, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.2621553805617084, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.2644420173449953, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4942477585038362, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.18599084133498495, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5118786242195569, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.13597984690621734, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3458330288507223, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.20402030918588085, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.456698795546807, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2309839071027402, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.49038835977529066, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.08868436194048783, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.3831080989149587, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.45698403959641504, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6213112392290069, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.38305744058127894, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.5478318338650964, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.24258147673307567, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.4209309051959654, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.5323299634491547, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6662250066806382, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.21820009804660956, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4781988345309841, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.43221578809726585, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5731291999928431, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.32971194511331664, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5743696901533981, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.3699456463838542, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5802398187253943, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.17822917800610066, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4151867931118682, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.21565717351206007, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.43093412084257204, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.3418125302637748, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.49442592936157403, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.24463616303656896, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.47836315300803617, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.17956658431980232, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.40953674896318, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.15222275337751698, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3357964670722481, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.09176232845253508, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3662849506582589, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.12443062751342439, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.23475988618545057, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.10074078347174975, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4196634384767732, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2421027255090914, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.43034076639606794, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.30998874327213094, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5576631273432328, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.11895105908708084, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.36047024705778663, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.14936222269982402, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.31574081509853114, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.19532472677364568, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.28229489197306035, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1871593662064507, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.2976064158089205, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.17743299460161885, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.2727203075505105, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.18732171292752747, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3771250747486541, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.10277283552544851, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.30275778273888243, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2311945565876858, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4191879346159698, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.22242657086332168, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.42530875747218794, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.16725758583047057, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.4301201864661688, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.2249207301180078, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.41620574629813584, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.08931590096116851, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3195248805327168, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.16460358737053557, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3762211520402395, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.080483139730987, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.2603682099909762, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.008644306419269237, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.035638819901027775, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.14213391357743071, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.09835845272625326, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.152904843780367, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.31008937332181585, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.29474400772477727, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.44093996056306717, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.24768872234171613, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.375309424077234, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.1377011720764204, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.27757197306209697, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.16775100491410364, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.30868449832998995, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.13258797836353825, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.28552565766604676, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.8107492451395732, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.900032747778274, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.8761560783209453, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.9484564543183253, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.7505336182671021, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.8401910628269498, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.13725861056573663, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.11147384852362276, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.13453927150397377, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.10522974272748564, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.22055493694673897, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3931965048763613, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.839587623092576, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.9096086668952811, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.6885326214539055, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.8229812189228393, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.839587623092576, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.9096086668952811, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.412295470431275, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.705800771033924, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3480442076026084, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6142483232997242, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.2861853478258715, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6401604432917332, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.14172292406325543, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.4762857001428092, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.17401517708317762, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.45006261596496794, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.151240443751577, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.4224869587588239, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.21850594525107195, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.4049269026117245, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.2028736642487601, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.3614856639698008, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.2255489037266197, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.3954925749722234, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.2466674257522263, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2929807168354841, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5975595069845072, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.6689604664235209, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.8010329764520807, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.4678134833959513, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5051480556620123, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.4113125177363443, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.42808075762838727, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.32685141385924577, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3758692873615971, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.27341185048222727, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6411651849711889, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.6237774736059616, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.8500131524897436, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.573764722928549, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.817979859532479, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.8482942955247808, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.9256238040654331, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.27483211854002193, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.20164065196183215, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.3923533979663226, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.4212555584968603, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.44264089366400194, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.25034600728678114, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3471790743028735, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5354826964964929, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.14528679532351443, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.45626264176882697, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.19496249079519765, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.3404780052299898, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.47631009147745074, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6668706097750393, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.3312076918041707, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5907489769215882, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.1481394578697113, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.4346232049071254, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.20217803037339238, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.4743589083194767, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.8492326635760689, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.9048530940348648, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.20828838183973028, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.3002418280717453, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.14710052131359536, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.2322531742374544, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.19427446513842178, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.2821379316874468, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.4962806188414642, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.6142754339875535, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.8862476419965991, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.9357668560693397, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.5181212746323438, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.6637469240656353, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4499781507152021, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5255804479733618, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.34190945667692124, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.38471892347518344, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.40122658664791466, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5789876781041586, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.28743011594299434, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.2803950119994004, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.45110582913319186, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.2818720423903184, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.3950106268119009, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.17793925745339384, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.28012888208050135, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.40533142214730206, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6060585353811423, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.326434800689293, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.4480048055728212, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.3861304705880985, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5248223977765574, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.36210097004176117, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5007651303154664, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.3875738939089708, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.6165609648382772, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.10593991511157044, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.12522096668112345, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.1209593074330819, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2476165058078653, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5008770061123741, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3187271473320672, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5308594426934777, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.20158074753947833, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.4601245932152929, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.08214465123593925, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.031835895924415845, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.030384560195149946, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.20687913047075865, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.22828954232316065, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.28479942163807365, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.3268532842861261, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.16442902274779153, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.2560785881872606, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.1420515519076652, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.44106281582354434, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.13714971174966237, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.40286739446153647, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.1420515519076652, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.42828528785491377, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.24187339355165743, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.24258882871985424, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.5303410271196803, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2524885334037127, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.478828996001936, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3276463794734248, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5691582878087721, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.08644426594013177, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3191159905793865, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5859514292713682, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.3401185071799048, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.46989148838686473, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.22911003908657962, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.47520559779668814, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.3842217688744563, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5778946517730051, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.2115210387013347, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.37360356038205855, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.10752875081378005, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.3325883825268305, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.20583079363601006, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.4354676264744325, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6617572899591347, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.687028746592056, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.7656691936879507, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.5948821108337683, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.7754376703404752, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.47992366044240764, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.5677112072864312, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.40283046047758825, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.6078521036010628, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.583899712825618, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.6318158012380937, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.3267294026204632, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4333271065990519, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.3875738939089708, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4061202407032717, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.4478039777693801, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4520078853554537, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.2284240389125248, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.14669686413046806, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.4859054130771095, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.2034208182228192, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.574929092637314, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.18818468056723417, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.35937272275747895, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.19394698940390126, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.26825696990387976, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.18661491233517533, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.2813929671493715, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.3444628323551915, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.09784168213672303, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.29894945474335277, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.1333681278040752, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.18759202316167212, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.29125622859770967, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.360056585428503, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.6205563386317268, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.2965712396518154, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.4982942628716768, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.31282656848317575, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.2635537115709103, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.09562406574442013, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.3567495948423568, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.10863331427699639, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.1545264805839251, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.1540863895003299, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.12991916506579942, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.15172157858081844, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.16857118556223663, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.16664773157279084, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.20610814612963693, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.39877487248588855, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.5310673226738754, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.35530535255335743, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.49317248045883316, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.3587511367366511, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.4883760305954916, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.12673718536830808, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.3654897220064675, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.2061477352156375, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.47004751394317756, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.14939354788683526, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.32530330530848595, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.3157547101764287, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.276162846755385, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.590708674573307, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.24111227980147207, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.4551171989910026, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.22537412722674857, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.5140931896637475, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.27668736912821895, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.40498166849882933, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.24623953025272619, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.4432077157216156, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.5626933387118171, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.7324678592100804, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.24622924391353238, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5061411895546121, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.33713540983351536, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.575216587193883, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.18512357977360452, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.3375501419021754, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.276824319389769, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.41668286331996945, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.13597796343834895, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.3135708685608336, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.25590356077469273, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.3573797368487792, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.21800193956058223, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.38946101797520266, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2046592065585361, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.36230063786538963, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.09520142487881139, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1596217869107113, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.34479856217047133, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1542516097843049, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3214558584292576, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.20891853890830714, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.4493410190472382, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.3892904392414698, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.7105799594213658, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.18838122823966647, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.3774817267101267, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.27571859863660825, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.6161549134554137, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.6147881529512643, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.8512585023349323, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.3451395513935865, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5966234405388378, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4874671560842625, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5556100337221122, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4125656013737127, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.47300889567828913, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4874671560842625, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5556100337221122, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.17059573701616804, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.3047807762878146, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.20600299538363603, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.3255301396673795, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.2599500366651973, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.670001214025099, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.8165101710241945, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.5386933265263314, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.7161301762977397, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.7743810851655712, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.8501530116907571, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.16698954254101847, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4261570418098611, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.05213452347557882, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.26774712462225825, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.16363363237367146, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4703098343850332, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.40784428374394943, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.5381101081489561, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.6425503166524515, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.7487396970714064, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.5538142279874649, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.7100363957633058, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.21552806748139675, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.42322383185606965, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.17166186698685532, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.18367413170243496, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.2675267612290173, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.3875448571474537, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.6080656767908881, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.26483859169215596, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.24826026845603086, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.1676784955078518, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.4080601696403001, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.2186976686325118, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.39566479324421505, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.7267072830982378, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.7866205781286685, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.5053915409642312, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.5997255667760161, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.565361573648609, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.7078194218800181, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.8078150978406724, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.9277882372664237, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4122868806605698, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6594447026416659, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.9086549610666288, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.9619796185510897, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.1854768778301409, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.32434904462209013, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.15756751766261828, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.3930524987681875, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.10289041531199654, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.13735392786968814, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.1529727623288305, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.3589485409071449, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5118532683220741, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.1504843536148922, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.40413967944464674, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.3073381334558822, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.47175704360401727, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.19918231170682932, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.13196931585453256, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.25888526562309433, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.13897158881271357, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.2586128831320178, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.22755587699269406, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.15923351303897038, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.48920516349347787, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.09857961422425707, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3596883714131735, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.30166728533047465, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.49325034878601914, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.5041350242010638, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.593218021252677, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.38403730312776824, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4313278522148071, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.1867326928627706, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.4405136963304348, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6684728376823417, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.8843946454355334, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.9484564543183253, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.25845327815429825, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.47631009147745074, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6947042435623316, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.47631009147745074, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6947042435623316, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.2082198320914845, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4623467870246507, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.30384451027588233, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6512504803383198, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.2080315522738391, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5621055754076354, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.11002068284361832, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.3834796809260055, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.5131275135405763, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.6459274917556753, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.2940242361968644, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.42080477541613315, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.2834458481265108, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.513372427519788, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.2653242203314122, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3884124015564349, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.2653242203314122, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.34894923767842045, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.11434800023292974, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.2765427274562731, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.25573580684957503, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.20221836056343176, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.35296675898522734, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6528129880382749, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.17840382725791726, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.48242888261061057, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.16513339589011042, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.31848886796533626, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3560907191428757, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.130145254194367, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3939630948438474, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.220561161454765, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.4391853573161077, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3498719376380512, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0675147309173167, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.33388033606118805, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.11123005554481152, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.34466307593766776, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.24323957127167917, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.5437359425177195, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.13737279171076758, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.500804220867966, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.14718371279247996, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.2592494576098376, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.5612265609510381, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.310441435588881, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.47844112187242127, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.21223633441554032, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.2461201947986108, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.33094680953828387, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.26333181655541393, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.30094298890378757, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.2718655706895806, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.2152312523781826, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.24225277690337235, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.21015671316214898, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.35725298833268504, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.24331740192945808, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.3669898885019683, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.4853134986602024, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.16133948681475338, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.3064239315441572, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.8003203203844999, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.9453478043428296, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.7215691881328408, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.735100789804592, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.4765874091118851, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.45911557772276623, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.45022125383821326, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.46874267375238576, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.2028736642487601, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.43458947791319813, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.3013901676230198, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.38106012955734714, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3820562306791339, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5488313413379253, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3820562306791339, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5488313413379253, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.38091370416670794, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.540550443602966, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.23189835231884592, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.44157797833899437, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.2294068720558097, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.40458364050078693, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.32588643749980295, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.31430120091187586, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5013155459452984, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.45237912327122276, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.6299071573751139, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.23736810439041953, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.4004852416401387, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3722001929300059, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5252698638532942, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.5605065818946205, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.586853267829013, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.36300296341860155, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5816676674074003, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.1258907882951215, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.34143648068854054, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.28765408533715414, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4046608868073569, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.1819722649161304, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.44254730215235283, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.28295596283263513, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6067794553589253, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.13305199541830684, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.43244987270004115, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.3377385620641691, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.5256128450453542, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.1175771442804648, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3103572690939351, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.12546912767038895, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.2651343523961406, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.12407216162020399, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.2664864612493293, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.5322520826224556, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.727131667480615, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.5322520826224556, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.727131667480615, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.5266403878479265, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6838125749299477, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.6144246566045058, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.7550732449201221, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.2092659579124333, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5354766759595367, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.1284866896836278, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.54959682211865, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5470973834864862, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.5703017172567459, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.78509136371851, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5226605904538532, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.289331164128846, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5798018459101258, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.32001589569502475, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5274343388526991, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.31869191523653845, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5973293882694002, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.20038908500140973, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.38365854681342043, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.6666467303030572, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.6471929785766445, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.23287896954139942, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.34835288582718865, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4126375622076229, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.3664818394063563, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.1404678994830558, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.470059848862195, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.37429964421261713, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.1475256903804988, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.412830471303484, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.3097707930450913, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.38964624025381533, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.35722668031235094, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.359712726799806, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.499435958665741, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.25381494737245897, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6023865926498774, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.20828838183973028, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.3919127720212458, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.3191922067457696, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.4322938742789178, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.302221525161365, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.494647923435533, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.14239015212277228, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.39011057458940945, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3312615528522037, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5044209915579331, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.379527516398695, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5401652761721537, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4063299618766256, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5674287431823071, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3642301318550941, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6103580099130892, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2878333693524178, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5587364816350978, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2878333693524178, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5587364816350978, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.2204887282071633, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.29000609768684643, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.4718372009351201, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.514371044868007, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.2167183006379162, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.22719782145384587, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.21061661601439866, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.25309156506322616, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.2920066581890844, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.36052310235569734, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.3813114671801389, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.39681350602982185, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.3032929624979452, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.6298789412741047, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.3841997815718642, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.7084389853258415, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.3212854967972961, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.5882101692160411, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2382939784364074, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.5141279222953337, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.46175494867931294, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2460137257692754, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.49701225041511987, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.11902001907030836, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.37006869202652387, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.09970617113450042, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4157699695564606, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.25678404806291744, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4451755318490681, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.1691896235111172, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4942911926258494, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.31029223530511546, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.49153218387646985, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.25748661016289676, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5470575132556847, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.29041376174024985, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.44402718863249474, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.37652399404345116, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.42944002472700066, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.2833048493206313, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.43070982670283003, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.28061557610476007, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.560457154689433, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.34973466192007374, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5437131659817407, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.21349332971500937, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.43940628135351467, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.2722704374402053, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.4630549375673026, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.2516546237169354, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.4948297815905772, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.2862280732631754, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.37692927868434317, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.13254512146117509, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4538619157918892, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.18592370210838877, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4365745598211089, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.5931895310669659, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.2560635441623709, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.4780977367484985, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.33626043540904865, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.538764562032814, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.2560635441623709, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.48856557052258637, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.270465701330031, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.6186468607030233, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4257336921268292, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.38564750221750704, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.20022731236728245, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.42151488713496327, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.3538049406567624, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.5074236666326171, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.3353862189849067, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.6098504982416948, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.6548615789183071, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.5395661538587241, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.15935678781360804, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.4521793911256492, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.18765818045694288, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.36437642049863195, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.3612915461819799, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.013618788145100353, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.08603830819648207, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.3014351160013074, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.3460021525794904, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.07403266639469167, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.14081073758628304, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.32836120166564164, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3353163646582782, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.25516833112291476, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.11679716931522291, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.3007876434578066, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.30300203366197276, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.4326017575964093, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.23310335053954467, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.524222022655068, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.4013786550577509, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.7311884014618186, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.17895706401541522, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.468904416935942, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.22221780818599915, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.14198034060416528, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.30810954638924765, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.1958174339824296, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.17923344640485428, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.4857079343907557, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.3532706340602244, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.36722366675256907, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3066439134043059, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6338650948810797, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5452372526683829, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5425084953777174, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.28875537786443695, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.47629875969455604, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.11141706023396854, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.39859597782994555, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.2345085086564769, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.49068926722541634, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.7532851335428472, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.9428927186852146, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.6575909538628469, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.8936217179505701, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.5143395284275514, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.7123933129689966, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.142420821179659, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.2037070724003624, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.08822666853435472, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.26516858757309264, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.4788683350246076, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.285255290869053, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.5150277853121517, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.2918097135253056, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2659411626151445, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5505575080111372, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.36194410357208756, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.598992373933567, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.28892136400127594, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4814801693556659, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.2533807666144747, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3199679830665405, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.24713133286179484, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.5503431628224418, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.4965709608247565, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.35395850928300787, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.5512586832695557, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6913832239874317, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.3815680677485232, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5272796429919636, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.5533750148426995, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6820863084799114, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.18239350853723665, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5454029225665398, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4051110969828215, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.2210196346762089, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.1460968145362594, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.4638747721441993, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.11653907453915101, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.3645009427553585, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.31718083000697217, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.2534148517150881, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.4516314349242959, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.15612566417343207, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.3498678433566786, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.19838325645746463, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3953826692542057, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.32347674230893503, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3581157136337445, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.08840994001530046, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.44402726611329, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.424690156353477, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.38370990452048254, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.41229278985309037, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.12231772169405124, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.4262272217222601, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.42709235715262367, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.15846019094564587, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.37619226030999653, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.21950630289046016, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.49771455694254846, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.26216883254914064, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5516544064070883, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.4639491362210437, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.5584011888296856, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.33351685300508205, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.46858342159783783, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.13203551444458209, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.2799958478061631, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.26763155480958284, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.4828657076086828, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.21339518760946108, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.4004950435730618, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.27004391647712717, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.4084384842894723, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.2028736642487601, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5137897386967579, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.19696330878717075, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.36322038790342054, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.2543081796362572, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.1458629230810952, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.1596451070396453, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.15005674613274578, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4083997317231223, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.17571400908328694, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4563418609671908, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.29482283350371896, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.5278627722123207, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.6793045635533688, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4291451835074721, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.341191474032336, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4705433400943735, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.3387562718376491, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.4907254093520437, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.14100024578768863, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.38811765582682867, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.42047387366535105, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6070400562507011, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.4393160369685383, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.8033601095520951, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.28051550320162943, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5856239602984719, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.419468515826214, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.7306819794111177, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.16953891950751387, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4759361360667322, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.42638539122035973, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3979397609409676, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.30166452953199324, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.4363965906324271, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.11692421557173073, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.2780081083837946, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.2742812949424711, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3621464793575014, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.31567959179972443, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.28374091032340426, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.04319276109068939, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.31240704409387926, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5481365257229119, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4207168232226367, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.1475816455168176, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5015755484727876, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.4154905708443904, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.2067973157835718, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.14030763768586757, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.25421938685023643, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.12568752960413668, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.15728631043405775, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.32952773497361293, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.08883879001303638, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.33545029773179097, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.13285178183204643, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.33120970279184225, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3429418991437785, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3054613864495082, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.32423566021380024, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.21388747780355633, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.18082588865422486, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.5146867759852178, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.21135930387565488, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.07849706978299485, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.08114854252363812, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.0912147892671242, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.40684061814045497, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.6155459970463403, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.5363590525255244, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.7030523716437119, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.4023605739267744, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.6645489548096619, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.17443259739075218, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2756167943711338, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.16032342647337483, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.2887138086538547, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.6342291345998248, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.20748131961458333, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.2716205232346228, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.37589902061551017, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.42554151277542873, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.20748131961458333, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.2716205232346228, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.4135171000263379, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.7050151549073953, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.42988105429544615, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.7577244658187771, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.5366411241731205, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.825566494253596, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.6976333495952621, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.8331572107884448, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.4165530720734658, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.7027805129995731, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.4027788021844849, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6872835607174038, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.498704623570665, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.6478746389895599, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.41307323705325416, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.5785653391533346, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.5248587176134882, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.6664855309004869, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.35210829264331733, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5239651686730163, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.17729842264695017, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.4103582047611184, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.34895836374229405, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.4767378358574124, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.833078701050083, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.9482515348146272, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.8958039312312598, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.9382091007325469, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.5805399561362194, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4810464260105228, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.4500531895417844, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.43027065541050147, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.4933292241270431, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5225247297523148, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.5064127215831256, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6516332048338376, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.5212982931053122, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.35319015092357736, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.5822934956325967, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4592978565863154, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3855522725905196, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.587260566914102, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4426623526629488, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.6368371029698285, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.518761522736185, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.19650854773882592, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.5134302167765095, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.518761522736185, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.5129586382458503, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.7857394056399366, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.5106109398471469, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.7688046995197549, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.44778459441351737, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.7043336945393497, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.6535194995338728, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.8909391457425937, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.6158161554766717, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.8568982835533138, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.6535194995338728, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.8909391457425937, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.5852187596735429, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.7147018027438421, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.8151678595510182, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.8873630455888943, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.8571061116877262, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.906026511295714, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.3682241310101735, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.5606184355158915, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.31684822717918226, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.4984008175596484, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.31684822717918226, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.41779931059703573, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.38216426442206797, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.25590356077469273, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4786634069414725, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.41469320341466864, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.3162730677141066, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.33514014117550306, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.3832378601967276, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.33488655580657256, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.7293017619227443, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.5709867732881334, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.898461683304813, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.5009303657723724, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.7151387779856716, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.4768283301747848, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5294365116477578, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.4115919883568686, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.32685141385924577, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.70370764261192, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.47331152665045856, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.8148863881905419, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.20352458275127414, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.6347163227772256, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.2175445226496326, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4621999154927885, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.3449754050963302, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5521970778133709, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.20304086026162935, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.42692494747660203, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.794834366062997, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.7747058711066555, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.794834366062997, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.7747058711066555, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.794834366062997, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.7747058711066555, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.28688236146427454, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.30588462336040045, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.13421952443691573, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.1672261435520376, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.1850334785266634, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.22109333005198922, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.165099903439123, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.3190887215348668, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.4863428828999999, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.5526778778205866, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.7267402732246275, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.4779289657345161, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.6131584716544094, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.6298777848185599, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.8784032559879915, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.4721001028256397, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.7096678127067526, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.4336560555138203, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.8096970872393391, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.285255290869053, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.40782828620425265, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.13072010980679707, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.3105434451119841, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.11967758950157248, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.2800855102887508, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.2320305803246989, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5875457251146547, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.37453249276032596, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.13471766853689124, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5276176357172093, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.2293648308471323, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.4184099073786108, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.3199526749905591, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.46625097311775787, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.43437903147819623, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.37595662994657586, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5278838809443244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4012179884342934, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.1751062735415077, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.48664097065107126, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.5129484309843931, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.6268186944844665, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.4111336169005197, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.654151133443915, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.3911104256806521, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.7162899586182385, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.23114663823833642, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4894179053435348, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.13566979610140004, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.38699631006193164, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.1434533437144611, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4325933876557919, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.32282138800401855, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5545363548814882, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.30702571862234085, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5270937279585078, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.32282138800401855, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5545363548814882, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.2520126751139802, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4174826402445743, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.28615556452106294, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.46306995992822714, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.2291421308389693, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4574939601395284, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.2286960004658595, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.4746698507981419, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.2898497051727735, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.4696277526071703, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.4010889714538991, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.5073411865094402, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.8522456714074852, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.8915710595176098, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.6917901740466924, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.8131122830944344, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.7124633354895817, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.8131122830944344, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.2152724303952775, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.414196892394643, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.164176659908094, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.41455341963750286, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.11824658049755846, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.3786431496602672, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.3309820868794149, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.18931747781986427, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.3742105986611897, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.23318982747725595, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.17210731663474327, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.39634356136021137, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3416664930284698, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.24371084210185487, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.24769802565621082, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.4703337695910655, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.48485170206034506, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.6080349479704925, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.24671763489589052, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.4549467666840918, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.36140837993649927, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5149871064681609, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.34185025753461284, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.48686023881748675, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3232534820704333, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.48025544762616995, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.3100943381862644, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.416673187106377, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.24835336815593242, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.3892570202624745, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.36880864175927275, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.46290260506783343, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.22759483012793272, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.7746087722406751, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.15821285888349262, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.5956452084834666, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.24065223308491276, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.7895361122068094, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.4883033428624341, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.7631727192799108, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.24895494253879688, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5641428028936958, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.47689738482638455, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6964624392461141, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.2509163300522903, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.40768446327474644, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.13738108161269025, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.3092490317326459, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.2605680717060868, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.3964513253420688, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5920251300199506, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.22872196013470597, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5536738597162264, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.41584686600540666, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5942731412808763, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.24524653576725172, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.09001463882570905, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.35606470318621675, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.22131099289519415, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.12085824721993538, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.3494963045761496, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.38068555329170634, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.4951270565975413, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.3046160524722292, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.5006657499823403, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.8895260356363631, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.9602241494544458, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.9574533680683809, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.9651456696916643, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.4772894233335957, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.6802859471885812, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.501310627231278, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.6497159142719684, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.5995278533842179, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.6317950587232596, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4622377023605667, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5631693837721754, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.44621027303028116, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.5218244384185079, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.38430061934674387, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.49614858773984216, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6104981438934256, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.479859141564773, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5641001468407324, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.3774814765934677, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.4990116884547619, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.3623885503140912, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.591097975732367, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.22116603634260015, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.46760899549728513, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.2699836537150582, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.18556675930109115, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.5038073544487811, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.47396838435140404, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.6824513472106343, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.21951524426618454, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.4465396346138487, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.14965975078050625, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.4312085220554114, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.35270822551668213, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.16731078418090023, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.3632099783723749, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.5934737473820053, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.5115509728992912, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.38358551832735843, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.37297693132140797, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.6079938395398949, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.16441798531606866, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.4740886351198963, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.1050176352370787, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.40362680831391573, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.501310627231278, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.625931526816525, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.5995278533842179, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.6130905930623375, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.6781394283024478, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.7591411004037735, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3247977183883475, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5194224997049715, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3714775072696357, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6057428008252769, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.5504220378177658, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.7644237788882867, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.23529269197764505, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.40809201669399076, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.14119598284201468, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.44173678486543566, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.235761566588968, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.32474347462386666, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.3814040834322927, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.1976684645555356, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.42459292222966755, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.36760622066825005, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.24297293935529007, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.20550295710786312, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.26306143053016545, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.3398238198012154, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.23650173894542376, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.5339293213731362, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6871710646631124, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.34756561191481233, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6088539252565636, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5257106921837311, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.17876827148517369, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.6129800176024777, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.34485299147725845, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.7179268969430285, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5554063047350235, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.7122051230572404, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.7814624520865153, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.8164795700243455, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.8966287960686459, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.3173673439991377, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.5749974286664644, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.3904439050342299, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.7513905732870811, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.6543503796047173, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.8630547387568517, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.31189530499557644, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6178467600806551, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.501310627231278, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6476336500357023, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.39363232658946995, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6025455732366968, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.3981101537239463, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5160821572366358, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.6163736299428778, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.7230511644674203, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.5399438397704499, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.6978441364968362, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.789917682435982, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.8127487880440298, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6743083618671843, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.26808424913615275, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6185283127358252, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3643840101054471, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3227335009304841, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.20019749510803492, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4550706657312225, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2481076483975817, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.38933614220345447, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3226647471194494, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.567577341013788, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.4571698763985791, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6457903784448579, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3467494262331134, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5076258119344784, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.2252707911092971, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3882698759114865, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.25381907882982485, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.2679490624827725, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.19062118739377035, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3561098113330048, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.22576206373887328, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.43106919861749643, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.22215063102831487, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.15004931283219156, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.43097718132573626, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.4902862637317829, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.26184495272448327, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.5568278384427537, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.36910468947138964, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4910950369957017, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.27057928415461924, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.18263245836368824, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.13872638167626056, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.29708830117546026, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.17466448960963754, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.26977779776316707, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.5502252143009858, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.5618268005152494, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.6323271459296715, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.33459343819025317, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.5487027389895724, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.29699464782947244, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.32437584698730715, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.3269663027436998, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.7511573912724299, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.9453473543978153, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.3450219162509876, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3993348853061597, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.5561195823338172, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.5362935676066722, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.5803515898273521, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.5422220468910552, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.2562150245540302, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.47046477830594896, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.33438299066966715, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5409759573191787, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.37854068916316835, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5743796566387722, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.5521710658453207, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.7317828775912516, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.45506803308128024, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6477506541284608, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.592313615748771, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.7382416555842614, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.4018202851356865, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.6003256951549871, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.4018202851356865, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.6003256951549871, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.580451128369423, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.7542976177437886, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.18207052811092134, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.4504432021668592, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.37717457428685847, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5554130492458337, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.31598923484911084, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.6425503166524515, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.8078891929749037, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.7629273292796576, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.8510385544954956, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.8725129388059689, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.9495292423959529, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.2147607499133801, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3976144917079093, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.49349163706233623, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.694445271037971, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3037643089519314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5183662698462751, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.8253498772794055, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.8529564805429163, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.7944837206494969, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.8784531740275225, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.23887527917609022, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5924993690004501, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.5828833474188783, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.7908226509294533, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.38694317759010316, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5953878513137957, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.3009687072297843, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.5341810386314462, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.5040673596100225, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6469962279041276, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.22816849039973935, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.49849908693271183, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5138104164912963, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.395494817172382, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.48210216762305635, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.1794560313432444, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5236301264596329, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.16111212240349498, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5162765195160328, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.23109536367862135, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5693079918450474, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.6486932415130529, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.788686710424071, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.4252891537802403, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.6269243845872724, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.6486932415130529, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.788686710424071, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.43937095446369234, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.46181721677136944, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.7490853969372642, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.7869453805471358, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.4970449067437269, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.5549084692917513, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.3460178707517162, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4777182579951077, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.46463179926223586, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.6658302112115018, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.30934066139296057, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.45568578346907496, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.41103851467561064, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5051296804607229, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.32375968335328725, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.4184987692475953, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.26583802173257376, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5022872142270257, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.3680806213583401, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.7106717690083967, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.33573064840973227, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6896084087753593, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.3294509143325626, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5502318837669161, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.6102624546684577, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.7455382911279661, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.6102624546684577, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.7455382911279661, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.5129914365244811, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6719058099803666, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.42219590199110324, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.18558816000270506, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5082547077193023, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.25104615680952314, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5386684376521024, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.35573896339264094, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.43373844074577966, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.4158130624959958, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5675993368017754, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.034234536820051814, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.5438653754915956, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.7302649909837065, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.391080327529236, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6466158388142541, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4464617303464354, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6719518780034501, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.47901455811287486, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.42929076670455985, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.3964023716675737, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.3718976854103865, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.3063889665164676, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.3060606492644399, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.1714049169603588, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.22748922852371126, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.21305956475594143, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.4395285386678049, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.5439405004075281, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.39022736644855677, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.6827449888069321, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.5194247346787363, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.7440660671846263, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.4093184131170722, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.6844082266550039, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.24268235789067255, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6128667394032248, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.4696150968541076, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.22656720908801994, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.631245192197625, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.2434623104231637, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.44265412961841627, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.2882258334128601, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4424981883607872, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.2882258334128601, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4424981883607872, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.37257484093951504, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5542570357348661, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.21281701380712922, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5028404616749624, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.15295559337528836, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5217846954711376, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.427700699409628, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.6058578812402458, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.4323312773819961, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.5997371746139766, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.49935841995256924, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.7295897846667867, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.29622254568370254, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5178269067077038, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.16373682488441257, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5249159229096783, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.29663479358211337, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5048860636204477, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.5616963280794934, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.4784684190704374, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.5220744129850714, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.42656860819541537, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.43846037099743423, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.5878523089199363, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.3049156495560148, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.41208793236807006, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.6396679416047654, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.8130954821598096, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.43504038103657183, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6606468296022548, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3265516873506877, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5955775050987988, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.25916413607200117, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.48625815319476634, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.26608125176434144, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4802266386987784, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.2966090320349725, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4660692265920593, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.19569434861872417, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.5843699612664682, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.19696533992407975, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.36270408031098256, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.7614976958373465, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.8451805980092224, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.8578928092681435, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.8885860675423041, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.7483293841345244, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.8285318099866168, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.287686670403962, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.5254267710927438, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.1954598432860746, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.5357843357785438, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.12050640089951394, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.46279589321598746, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.3723091902601643, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.49708772465236206, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.5196976495259397, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.5717810489005831, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.24010981785257499, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.3038497620512514, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3866478782027105, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.34136898121736164, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.37814378041895597, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.12092350598744767, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.2611572619156785, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.19422069098763883, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.3990712046437768, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.30688403446731133, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.40760363566240154, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.5022374395202223, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.7482826302429207, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.5696767062759219, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.7243872738436123, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.5418739057997506, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.7260522735532127, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.36168074485009266, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.2876470433414085, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.3597009865964047, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.6496072343867388, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.7860533539734559, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.5049567629086866, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.6875175437591383, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.5856596027429395, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.6515526423776998, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.44363569462622243, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.7152578718641567, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.43527713779415106, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6492012081783873, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.4239615629447832, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6750973651130794, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.28770035113017345, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.4824112481129573, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.27876286341624873, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.47006631105227237, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.27876286341624873, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.4719699809379796, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.7288605134576496, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.8188207446751512, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.6725157402359803, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.7771536167828895, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.9067110266941047, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.9136710157809076, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.3511161927593497, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.44838119776698643, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.33088444297120406, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.4331966918623851, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.16570229441828108, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.5183282721440023, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.7899968492664415, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.4929664394953523, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.7163611428663252, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.419793811546288, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.7030875221285298, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.4071651792954847, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5696223051382897, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.3162277660168379, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5598397806456028, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.5087423866211807, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.6733471820130715, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.25797975216980157, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.16727613178248177, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3242750412187524, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.11856660123276004, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.24749625714009152, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.45242529056256514, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.6590255708265333, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.29591590531645884, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.6473269347851542, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.3789185999473403, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.9000001338525341, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.9362876355864519, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.7151826245402508, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.7968074166631015, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.9000001338525341, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.9362876355864519, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.18157374168582124, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.3223976983915171, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.22215846062674394, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4414547021536916, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.3082642374230144, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.45792726647338766, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.3035835725488823, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.31652994594299083, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.27254857143793515, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.2698809072033866, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.4390426411234037, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.13952118378975725, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.4232954460226121, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.23979583131036644, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.19120817575042512, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.4557967473618706, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.38977903534687897, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.24340568946986127, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.49124158433111575, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.6549405194208391, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.12861981016228477, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.48957545062365976, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.2698809072033866, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.5545874741798575, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.4329139718650503, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.3585323035168672, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.2592494576098376, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.5573927865354532, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3769395725981285, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.512767465109827, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3769395725981285, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.512767465109827, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.38269604012326863, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5200002010352563, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.14852672034924091, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.3094792226745253, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.21787417256423566, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.3876689443198751, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.2801269471205747, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.2703977722123393, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.44841562670836715, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.3939492854375959, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.5897931522810166, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.2881761264465535, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.5171031329358884, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.14577432272792737, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.3485312345680104, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.26329599886727373, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.23278028502053263, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5035438414330208, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.23256783267618808, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.2503888994539979, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.29117376371232984, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.1959572889882663, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.47526287474947615, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.19427446513842178, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3989194575281647, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.23317448188282916, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.26667143002371785, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.472538453999306, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.35138749399652214, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4696291825462069, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.16731078418090023, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4141738376060544, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.30778741582971547, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.5130815842691727, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.6347346879982754, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.8012052767784481, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.4044405568460044, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.6621599148868252, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.6848075777090852, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.7973909673112908, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.5406697535191133, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.669004783760823, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.8172480674634086, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.8884449620958097, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.5792652217448795, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6407626172619735, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.44411712310948115, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6797128514623865, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.5100759298724028, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5779765318107316, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.4317853842116786, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5210207497435424, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.3010103123092385, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.33667089470100775, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.46112487179211115, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.39930425989686696, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6331705656079759, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.10332090908268508, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.38232840987382055, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.261609050082693, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.14198465334075994, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.41732035784825816, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2620499195763038, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.45536529760795086, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.398116228128051, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.5295736590451592, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.7304847791671485, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.2513073726775429, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.46777360451268357, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.29218790157077157, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.17869133709232915, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3044932648594964, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1748462645190237, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3066192361421124, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.17832499439115537, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.37164490436142156, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5019119409563002, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.2608352075029667, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.2756134147603395, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.40663529259554226, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.124420945512177, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3252636443012772, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3434676785325562, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.14383482326455638, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4802954812345209, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.10375099461814634, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.37536190411744585, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.33140473433925555, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.10066789757060902, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.21673270446328768, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.22918023240505858, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.09279771067975602, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.13256098526803148, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.2310325762059593, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.4527304959287235, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.4389321784429702, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.5672441723286317, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.21488309480401357, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.49730166693272293, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.3010782087051575, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.23176692681985775, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.25533887786336174, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.44711013370113256, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7319347493436125, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.49023502313124495, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.7638414724136195, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.4424906782646928, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.705507971295129, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.21326369102393236, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.24781828193168487, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.07860105393900486, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.09678377693633947, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.11601141307045003, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.21671187566850864, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.2577716972449781, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5171901208397282, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.35015224715252113, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5701648579139658, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.3349252032650068, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5908087431574293, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3274016883618531, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5570399656004248, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3449058130015412, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5365619830343804, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.29688845677442144, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5494319015457763, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.207314191412716, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.4360555836773355, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.25376032254696296, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.5334329403985332, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.20039141607873007, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.36123312088832493, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.3235473265529593, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5441122251341168, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.32707695373369694, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5166643606783462, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.3069937936246452, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.5024648105961349, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.26513488970168847, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6029932145447834, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3927237741677927, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.7451438087039315, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.5570357635362685, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.8116469942298856, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3860973950960897, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6271680934322363, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3826576187198625, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.6071841372061269, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3447241447679157, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5531085140985558, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.27710310401156996, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.5216248191624099, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.31128635710849173, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6304411194127884, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.13308561809919006, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.5312476702183977, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.20475739007221866, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3934874462686164, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.2879556779114461, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4554184077174173, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.09578921953028982, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.40472887922389433, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.4730742700342366, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6716818492415609, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.38729516708438194, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6571482446395243, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.32995628251235876, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.5982616321404195, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.20057225201358211, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.47576367606491715, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3665528144045068, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5966563047685359, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.2587297749908005, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5132023401682766, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.3151295371556651, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6242597159052685, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.29894673648596126, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6322815922673689, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.18330256089173447, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5328391139635578, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.5295672450222603, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.715157413474444, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.7416488036617811, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.9156308978596118, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.2924496936199556, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.6040522123603048, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.2995728063785384, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.41824297302824903, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.23119301671666287, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.354782287640505, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.20419333453691463, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.39470297247688435, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.2356808688936941, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.6055769871534641, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.26230609318615344, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.5822825437641462, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.3131514736435596, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.5852253917268062, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.34259841795512924, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.585466128440694, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.22551665711721375, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5279805413050443, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.1565711240691367, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5086519720619103, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.1314770573188977, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.42247455964888564, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.08905591495817854, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.39258991796140724, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.16839298730242253, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.3815455050057558, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.2058592651002273, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.4968187716376065, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.34140765467102613, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6319466141042981, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.22592501932697184, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.4846944833505256, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.2682764485524619, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5066876769170529, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.24572492027154266, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5262167453128139, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.1809849704111973, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5183477609966307, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3348767210373086, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.11543246428739175, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3867652322513648, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.1752510532254824, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.38762928139075753, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5446552031353901, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2574866101628968, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5192222793733214, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4165851519399544, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5626264040219835, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.18968668542064138, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.2062407699777119, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.1636538054009315, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.27030640495259156, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.31172573638980083, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.45166421390889583, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.2905178491524662, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.4540869803464816, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.4416037594311788, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.5926552552596459, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.4286493815549817, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.608929454341427, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.5441799557959847, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.7471708187115776, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.2737674171768533, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.49294682774777393, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.24691200113491704, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.594269344169987, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.36092600834422417, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6496714079703786, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2322365386782331, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6044384701497908, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.15435869219704992, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.44156603809589606, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.21605302662107204, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5282568801368064, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.26458538438609513, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5387766932929448, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.09757710283079672, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.41975185347384797, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.07228800742761465, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3524948213332762, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3972317449044497, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.4516989732837159, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.5415798785310697, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.3972301056942388, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.5673240077710876, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.27691593390925684, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.397254897780366, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.29808592153996283, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5278034227464174, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.37566372103146395, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5970100838075844, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.37989456711162206, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5769558960935135, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.19943370880401756, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.5118140585073162, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.5136268735913038, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.747250567370702, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.5269786261674732, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.7211839703961767, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.09697472565363051, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.3745932362705387, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.18473000217570404, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4760100031203425, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.18239336435292994, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.5029345390359463, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.25259068609065677, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5384891408722134, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.24887831362342314, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5200881906842448, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.24135344239900156, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.546651751367433, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.09561039442149676, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.410158328815622, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.11290965451231479, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.4125077608038444, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.09225101275784285, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.37350112612982594, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.3471239643495614, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.5206611437816837, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.08961889092065865, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.3874168292468809, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.08100859619233457, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.24451849449561322, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.27103337618153645, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.5640525084856031, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.384089730116398, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.745723691136233, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.32244421248930727, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.647615627796667, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.9087119657256413, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.9560455759500431, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.019979749853566316, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.16655520792269457, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.2978831898624651, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.055358855900579915, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.08441965713154952, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3089195000557714, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.10224003680109194, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.43617932503833745, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.08610814090366911, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.2808850562492427, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.3951799525041884, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.5778309496373982, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.3366701635309648, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.5410405158608997, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.2101485462573989, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.432324099789087, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.12174947256163497, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.46773004477276736, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3106867450120684, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.6219524559268158, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.15986509194135143, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5267000984208814, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.21299929835435763, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.435252897241854, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.40403057670242104, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.6369130541839939, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.20581560303679203, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.4423856837970847, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.12351026307731532, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.412497189904211, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.23545536435121683, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.5385196954654492, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.26585394939983104, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.4531567783270482, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.3581233108133512, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5681591513115792, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.5411668461990086, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6522264060979466, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.2989125578949377, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5919388623239312, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.1456594557011165, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.37283362365421463, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.008318556718037537, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.26079296949054936, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4683174146167095, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.313279920188343, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4874026443611231, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.312235987246766, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.48588160953552434, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1079864637785236, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.22429322594709664, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.09638209202576767, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.36140609257046646, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.09704066931673304, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.21746317771363752, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.1662362263248686, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.3954564642899918, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.16004579189194332, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.47245794353514825, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.19803483846782313, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.48499595181063654, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.4106421326776598, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.7234753107719588, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.3109995020889346, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.6239402221019062, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.29885803796555876, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5453318063660885, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.308591734625294, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.47229626882753806, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.2639855268912507, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4723046890503893, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.18245182973446727, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.43628086807089367, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.1799424456747602, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.483712340915935, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.22310118314393076, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.48996223146164697, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.09108351723640423, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.3753289604442426, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.36733064093075246, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5166610542835689, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.6400394598805441, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.7975136683846923, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.2636617253730958, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5820502899836056, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.09931887908771599, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5290709591963555, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.1378743489117572, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5086655694099045, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.29502343631964045, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.6084768644437066, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.3203709331713924, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.6011010434667033, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.42100166812465206, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.1595594727127383, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.4576211976748643, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.10078945601268775, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.261100760720076, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.09253405254882056, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.32379787254738834, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.27741626606602926, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3189379698441311, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.11749577060207901, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3982271272491047, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.031688534538597726, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.1890804036427279, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.1273184616076436, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.3854117498605121, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.19425852569761656, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.49223809908076244, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.10485465064884184, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.32492314763382363, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.2491671393077868, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.4968863994886645, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.11317455078536574, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.45024294423829864, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.19572923134753795, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.5295330264022122, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3284892459410516, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5241940555676348, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4333728840229128, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5891294993540688, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2630714263398001, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5158255160824443, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.05285535428575768, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.09737192246778478, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.1807196053330159, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.3965678244961598, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.1781762226766203, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.34132344846940776, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.03433235964400958, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.06208764634995977, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.26302014232397014, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.20778408193957135, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.08712386724565187, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4181195306395242, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.20968620727095338, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5464020265142666, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.1954345051420573, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.5330042985514847, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.17197056422381857, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.18342876748823245, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.20686289430930357, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.023189147281557864, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.1828605775949752, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.43762946682189374, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.25874549081196363, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.45746164978998116, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2979184100665707, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.6419705855699708, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2930190257785366, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.6713003163919651, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.31164730348889336, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.6359774323093672, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.18212463619188357, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.39972650121479075, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.4752769115696177, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.17484203645083327, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.48749480755149777, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.43338271162956393, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.6374354417480721, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.3324045604922567, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5837709820195482, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.31609768845959424, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5673141497742401, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.3923185674218498, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.5839066770456797, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.2932716844020195, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6372147855611874, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.3429545250720308, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.6338733776441033, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.2256335120807399, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.41142902331306563, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.27518912165164433, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5271056340471697, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.17035865562294203, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.4491431969626715, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.10925485406610212, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.40585265442330004, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.13953680853761288, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.36641285502598664, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.11929906740245497, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.31766803297095625, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.034925844078130285, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.12176905733039614, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.36300532343703745, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5885664760313373, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.21789876624905538, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3682819491047234, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.09257776335697764, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.4234307006910246, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.18347190231449206, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.4239252832108403, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.19461047263115017, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.45988413428389885, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.13139217875016063, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.2663715525584477, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.07746741482791356, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.33235742788356043, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.21905325152754598, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.3163506555011039, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5609222668505561, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.21270966597282465, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5460005359719966, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.1769715756286121, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4730914561312012, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.07799070710306764, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.33308031587923975, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.1409579985182915, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.48389215304595906, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.11862036075744598, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.444201724436452, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3133814893022024, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.07833962045925216, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.4012947847397506, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.27588069957732886, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.01170165350096746, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.10692719022071172, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.20917377194877063, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.10184861034465903, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.41377038486289314, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.6103253550829261, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.3380920573004095, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.5109739521707614, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.3234649237345335, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.4780933016980809, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.02205958411600357, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.34582774491793894, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2893596714040359, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.22816849039973935, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.5295534280606148, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.348007986647201, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.6148736550683231, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.31222258402876674, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.5549937870516303, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.10721126066665879, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.23683075175361493, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.2631328190836655, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.16455392433653304, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.36033217429111203, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5707860320039717, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.461597801606675, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.6280777654467244, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.4224298950114519, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.60823085524287, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.4141871474340027, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.36769040719718776, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.4064141882459388, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.3096036988813059, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.5894510883198948, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.3286711939680359, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.5944310794747374, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.13547277341758465, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.4830189619506113, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.23841754841770157, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.34481325534410395, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.2822535302220024, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.3874773378787974, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.31747697264511426, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.40797778663955364, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.43368945552925614, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6793717376740783, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.46935933364934335, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.773055573548356, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.43368945552925614, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.640995178057518, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.20050320605789015, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4046291070099031, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3160213610127146, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5165614670038283, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.30758744700466467, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4684197705189288, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.4161791450287817, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.7054426787013603, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.2961516536011624, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.49803924348035766, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.3459667618766101, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6170810606402402, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 1.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.46832763312452297, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.8176110134774669, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.9436043261706615, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.9880191679951993, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.2830789070123405, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.41858897147271634, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.4593546097889176, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.608602146246901, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.23386786214190372, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.46662929903381617, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.42067720018268145, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6309653612961436, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.3397180516736864, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.6494995648532881, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.23811989337799513, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.4812080785035883, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.22166358657237664, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.45834104234305023, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.255918614113723, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.44318862516624546, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.35285733014385007, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5945202859296662, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.2460137257692754, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5397894338370378, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.2809009542151822, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5819888906713027, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.4573889291137309, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.6974989991762017, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.27185330211646, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.3487575221722675, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.15824382329465247, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.2847034639706718, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.1954328575417037, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.30293053536483644, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.27914759735007616, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.3778334876813023, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.33758329691923056, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4156592381734106, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.16177172185899982, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.35656294562478846, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.1196671345116598, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.4250373762074513, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.2805776238834007, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.2149405271477231, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.40802426587644575, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.2551158426117226, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4338792723307896, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.15426765696281117, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.36404432411255067, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.35138749399652214, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5764814746526004, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.28859523083492383, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5243060035864178, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.4258744680390019, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.678077932919771, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.20690996611611379, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5406044734296481, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.23626187156344583, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.5259172349664247, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.14065108796517406, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.4653016103437884, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.10556737722881891, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3637736731596556, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.2840158072494531, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.14669785543513997, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.3937770501596208, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.31123452089299364, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.4756674690337691, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.18506115334020554, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5096863469728294, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.11596632790546842, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.16510653858282376, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.14514613027046297, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.1479818938322678, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.2188350647878129, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0744575238654659, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.18081240117184907, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.2406197931700809, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.3480566207137981, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.18762960550870147, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.5048762254598883, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.19089395298343978, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.4775461600364851, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.18762960550870147, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.505905280342391, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.35540164109034167, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.5028380576753965, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.31087084319061986, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.48493403576578487, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2843877927900334, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.5287507679912548, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.15300252291898875, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5221038026847953, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3724134618099435, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5411724478620953, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.10991514729498916, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.35889788560857044, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.32692597326475636, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.30229895292756775, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.32013836373742083, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.1784284488020755, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.28915891965402907, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.28819072249233424, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.4281025086478473, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.1722187017293513, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.4101544500733319, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.09500509002957103, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3165301597200995, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.31643186523025857, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4990369740896189, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0972760643475914, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.34268917796251985, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.11183447695967942, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.2981154499191547, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.29160060199573634, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.41859679392459287, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.16457404825501376, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.33333438552725225, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.279651701540242, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.41325325835097537, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.20614290043638034, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.4026346891273123, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.10458125123016462, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.36412391917812675, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.39284822049881124, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.5731994852253092, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.4419177841121404, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.6137680308213187, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.25567957494892185, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.3876058827430677, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.32284785906314306, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.5391266648881738, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.3914713795199333, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.5396649879183305, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.3049871822195904, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.5208588286358844, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.33557244321033963, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.5209156086024106, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.2896941452360586, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.41709543651974984, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.20254179344857384, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.29007724698820536, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.574462622391897, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.3125048656450529, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.5603859508222943, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.2267246719280858, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.48581943550245826, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.3674833290337466, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.1929103437854986, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.4334775243896179, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.09709355995288857, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.3190240812909853, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.21418093872225227, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.2171788734284664, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.3041500319808576, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.06534434987768793, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.19191970942691858, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.14710052131359536, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.39474728110016194, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.32758099155045156, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.2954141956759853, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.11781409318573131, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.3064743661860543, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.13399284752024776, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.3533000786320299, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.1334209353325791, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.33435636843826655, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.34319152953492454, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.16755318066668218, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.5076991427590911, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.15483009791264127, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.421644120450493, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.16135142241763387, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.1143433820088083, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.44706528758842706, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.1504843536148922, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.4754016977092461, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.2103182834908572, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.3252172327778091, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.2103182834908572, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.31189147517716775, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.2034131578022728, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.3250035615909008, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.10758299612696903, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.3485199255336966, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.0936186743453751, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.34343520280095413, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.11007482046907661, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.37477767256456523, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.10727295782787309, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.40945621258421, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.10601317434781207, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.3549608383744777, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.2842642186201746, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.1531024544118244, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.36865141579883465, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.18672196092380966, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5755041733882698, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.16591958445638164, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.3816020524781071, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.09131381866486066, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.19526867634454675, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.06313050320435959, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.1334209353325791, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.32197244359239063, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.0953796259494125, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.335376322187008, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.1136025775201101, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.32399192578787606, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.14319746539576667, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.38319285812856063, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.14743233570338127, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.363972079338474, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.1758556937351426, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.4271110965918086, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.15112446346253322, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4582754568242892, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.15340824575172546, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4948861786840383, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.1591469869206786, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.44132589683753737, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.12288887055424895, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.43277999825597285, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.13004139997277986, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.4607205290066856, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.39609017426771376, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.12131345516615005, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.36539799614653956, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.3231843559409337, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5434967300739557, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.3671001023271087, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.5548530261238012, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.41031782909564674, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4055071421603482, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.37299539088865524, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.17950199148531412, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.4270012392614725, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.1664106020945361, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.4280857917577298, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.10157474763584896, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.350309379624823, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.12626953198628743, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.28923398754126967, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.14344436925456175, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.31855029095203735, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.1450561148847636, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.10052035011320741, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.31620064580236706, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.10628732960069, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.3283974297647533, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.07866142497287454, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.22436847715795769, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.11850541740049741, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.3765127698761297, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.1535686541317235, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.43682738448704195, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.1289623877962874, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.29257396221266196, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.19422659659588543, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.4406265906948898, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.18245501785036272, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.41711042074816285, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.22481074167380632, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.4682073476065324, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.33626043540904865, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.47970564640010444, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.3087246340317326, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5190191533554683, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.4909991753827356, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6181007830367896, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.07730563279435597, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.3100987773946611, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.149911771227821, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.46600977419086265, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.2344392143175243, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.18055689930962057, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.36732605723857714, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.20723638316347853, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.1992845824168194, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.1828540486873082, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.42270228247804714, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.21534597645653109, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.4429153970503551, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.004468275245755138, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.13136586691610921, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.16742936811875977, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.11940504610649601, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.1504843536148922, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.37031670283607354, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.13597796343834895, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.30423050739361934, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0993195473228234, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.2774071822336668, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.14828912728661656, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.37328040148644737, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2974539240705033, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.4914860034714028, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.2966236662378785, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.3980586645261528, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.2817858902060068, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.5812000010572426, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.319143328029808, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.5439628345852634, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.12584834793909203, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4359538673356259, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.23944732810452216, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5585059996994121, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.20365642689242272, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.46771026250334335, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.14258147236508803, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.38105995944362, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4149221101337332, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.45080523333135825, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.2497481028437212, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.3974751279392944, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.2904391540454532, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.49418835371490716, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.3349675354847837, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5234207823607111, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.12371456571439915, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.35562282938981676, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.1274115988406287, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3310991575890784, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.10982839842078235, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.25807556121990866, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.23391395118711963, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2918271110182603, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5908408959428468, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.2999540940698276, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.2115594277679545, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.48937379669245845, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.08545148602137898, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.36368508833748336, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.05837196410192872, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.20919043801522816, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0763518370649764, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.22203628687051016, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.06666337489197861, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.2641431149490312, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.23218076255522052, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3454863565779109, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.1637083741560297, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.39068717380984525, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.29620044168375165, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.38507704427342426, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.10373198738191458, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.35910226518392213, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.13539161487207824, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.4090157301700233, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.11401806409768651, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3199134488826683, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.15154847535138072, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.297329314233632, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.11546530656868825, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.2652340411459836, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.01803434118675279, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.15161074985415177, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.26121051953869123, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.12365973156022511, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.19243566997831077, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.07634618271335385, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.23992292805624504, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.0977380780819774, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.31987184819447434, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.07526631223214, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.32200266452557863, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2541074256214778, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.24384315520084382, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.24323684546156932, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.43103580001357805, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.6690742226623104, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.6031612036218008, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.736286703381354, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "bleu", - "score": 0.39432344823662835, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "translation_to", - "metric": "chrf", - "score": 0.5943452555220106, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.10772332006118607, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.17652714369664665, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.11254397891886614, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.20623288988983426, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "bleu", - "score": 0.1100081929352474, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "translation_to", - "metric": "chrf", - "score": 0.18967061672400035, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.27190910124573536, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5173567851798608, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.24493390281390082, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.48113625107113883, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "bleu", - "score": 0.19476681308252697, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "translation_to", - "metric": "chrf", - "score": 0.42030407727741037, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.429512074830509, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.6066779955199886, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.3459789902390003, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5620330456296532, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "bleu", - "score": 0.37825713491091884, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "translation_to", - "metric": "chrf", - "score": 0.5584414289480568, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.09596136927307748, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.40849147213099996, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.1845747513433909, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.44379971518505973, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "bleu", - "score": 0.18212463619188357, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "translation_to", - "metric": "chrf", - "score": 0.469592540371137, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.22972631482860506, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.436102988762466, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.2517176762753373, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.45137344500317134, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "bleu", - "score": 0.3128384316903283, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "translation_to", - "metric": "chrf", - "score": 0.48016279207050283, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.45026965676007474, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6668256174353906, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.43200638115383627, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6892273787708799, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "bleu", - "score": 0.341195158470265, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "translation_to", - "metric": "chrf", - "score": 0.6539473951166187, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4710260495003035, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.40475700826319555, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4349871720911447, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.310186302993101, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.5434540129901786, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.5244380103905697, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6914581279144536, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "bleu", - "score": 0.4472834999328078, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "translation_to", - "metric": "chrf", - "score": 0.6457130269652316, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.17207258849758605, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.3052503498954155, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.504154287515855, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.6074467585243234, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "bleu", - "score": 0.18771816026273827, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "translation_to", - "metric": "chrf", - "score": 0.37594160796244835, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.377949467106015, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6288808546806746, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.33684416564135483, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.6173496967095872, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "bleu", - "score": 0.21054588509072256, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "translation_to", - "metric": "chrf", - "score": 0.5020237474009813, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.28341626687166926, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5869314876429665, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.11283678603002038, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5027560731174364, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "bleu", - "score": 0.29432909534200313, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "translation_to", - "metric": "chrf", - "score": 0.5637465580755235, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.23399485663908418, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5631067041333725, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.30894994002746395, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.6495798576994254, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "bleu", - "score": 0.35806497640912766, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "translation_to", - "metric": "chrf", - "score": 0.5522671396375264, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.1793410088328766, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5126133936832279, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.25325897139464854, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.511461689033225, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "bleu", - "score": 0.3730973285213212, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "translation_to", - "metric": "chrf", - "score": 0.5926422939507472, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.24942094354139677, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.9199349282509897, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "bleu", - "score": 1.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "translation_to", - "metric": "chrf", - "score": 0.9199349282509897, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.19355919558818033, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.3931759629568022, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.162496560019558, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.47693678197649336, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "bleu", - "score": 0.21126480857843466, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "translation_to", - "metric": "chrf", - "score": 0.4132516611502927, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.16743424359150172, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.43311618815403874, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2044743996680912, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5296253104099969, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "bleu", - "score": 0.09990095999535835, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "translation_to", - "metric": "chrf", - "score": 0.43541588074965143, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.2089685256289425, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.5333424925429209, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.1689554748507331, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.48752020586891187, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "bleu", - "score": 0.09863022371664866, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4410680148316049, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.1296922311601412, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.44753695206116967, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.16157821959747307, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.5255622543684244, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "bleu", - "score": 0.15748430756119847, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "translation_to", - "metric": "chrf", - "score": 0.530020236187551, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.15415302247076879, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.4123343961300446, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.14473479197868241, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.4413634590503217, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "bleu", - "score": 0.1842259592735289, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "translation_to", - "metric": "chrf", - "score": 0.4512010919409926, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.18087140599571747, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4377272235852682, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4566114002517467, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "bleu", - "score": 0.21245026220526622, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "translation_to", - "metric": "chrf", - "score": 0.5450614695192502, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5469867443567507, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5049599536473849, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "translation_to", - "metric": "chrf", - "score": 0.464305874546181, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.18034760660633942, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.20587735759782932, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.24468026894076475, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.2749771763892432, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "bleu", - "score": 0.24399387658656807, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "translation_to", - "metric": "chrf", - "score": 0.3044305895074006, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.3147902135663803, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.24977763651196191, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "translation_to", - "metric": "chrf", - "score": 0.21237639792675794, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.2693653652960018, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.5351323891749961, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.28494569863631247, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.5314415165747192, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "bleu", - "score": 0.23269544971552114, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "translation_to", - "metric": "chrf", - "score": 0.49749977919083926, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2503202840132539, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6628587960881935, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.3780253819893537, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.6691463628105327, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "bleu", - "score": 0.2764824153808333, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "translation_to", - "metric": "chrf", - "score": 0.669057962133461, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.15197630365858814, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.3903562094322204, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.2991476612258654, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "translation_to", - "metric": "chrf", - "score": 0.3082702687589522, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.17677215260187162, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.42492794367017145, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.125959010609916, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4578429795465262, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "translation_to", - "metric": "chrf", - "score": 0.3002210625771089, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.22312700803550112, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.41892404547996925, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.2686036309072948, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.46796278650100787, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "bleu", - "score": 0.32114886466116627, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "translation_to", - "metric": "chrf", - "score": 0.4290130719589314, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.38791398909746805, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.5307069804730096, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.3021887988636079, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.45419878739503283, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "bleu", - "score": 0.23552484042758592, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "translation_to", - "metric": "chrf", - "score": 0.4709821983218137, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.15942530661337126, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.5151997420421937, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.26012602101891624, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.5371799694530636, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "bleu", - "score": 0.14137375964454066, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "translation_to", - "metric": "chrf", - "score": 0.4881276325562942, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.3280456612129034, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.05156674665890638, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.36698218242626135, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "translation_to", - "metric": "chrf", - "score": 0.3430290995002961, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.10615684540251687, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.460046617317305, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.09952498083578393, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.3978595245805609, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "bleu", - "score": 0.10916808066739564, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "translation_to", - "metric": "chrf", - "score": 0.43671495255219495, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.413922696186207, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.38459672847260074, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "translation_to", - "metric": "chrf", - "score": 0.41318454544592675, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.13839209880933745, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.35315147740153213, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.14073835588074438, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.3186851468537677, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "bleu", - "score": 0.11092528636668526, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "translation_to", - "metric": "chrf", - "score": 0.31604383600836816, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.2209022359029063, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.5243023558160568, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.27300740971755855, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.5381314258991404, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "bleu", - "score": 0.17139917523591472, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "translation_to", - "metric": "chrf", - "score": 0.4864810046478068, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.18174134858444663, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.48176247427646596, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.3065887048692417, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.5157029274056539, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "bleu", - "score": 0.18604195434563767, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "translation_to", - "metric": "chrf", - "score": 0.4122715353511428, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.06195434067782697, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.16175760521413005, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.1063765571906396, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.24881090381462032, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "translation_to", - "metric": "chrf", - "score": 0.18900561821854683, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.2868359127518435, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.34494300151091684, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "translation_to", - "metric": "chrf", - "score": 0.3626648377566182, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.11552139626294972, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.3398949301287284, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.1659833448676102, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.3769282770836756, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "bleu", - "score": 0.20111668406029967, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "translation_to", - "metric": "chrf", - "score": 0.4330800722857856, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.1253868308634287, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.46617501074123047, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.3130482255340303, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.6463371475277107, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "bleu", - "score": 0.14582974563534895, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "translation_to", - "metric": "chrf", - "score": 0.4561374068921452, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.39062260559157314, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.11476846027014086, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.3716193833315997, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "bleu", - "score": 0.0990145402804052, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "translation_to", - "metric": "chrf", - "score": 0.3832964227606499, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.1103430168770977, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.3888835203143206, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.0820956843607846, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.3672961979619499, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "bleu", - "score": 0.09351434853192983, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "translation_to", - "metric": "chrf", - "score": 0.3544533317605768, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.1346186114956404, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.4525877580002142, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.3826135556435099, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "bleu", - "score": 0.09469433563240592, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "translation_to", - "metric": "chrf", - "score": 0.42242458160008445, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.3003667779466027, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.12988310144953827, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.44924139159069637, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "translation_to", - "metric": "chrf", - "score": 0.30212704629782045, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.2850404597553743, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5124976639796699, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.15453491615716408, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.46885369942326544, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "bleu", - "score": 0.29666196021313485, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5228686595434603, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.11148956644753055, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.11036624147130886, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "translation_to", - "metric": "chrf", - "score": 0.07967090534466029, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.1756638973945762, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.43710438313784017, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.2237029203522163, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.43143618833956604, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "bleu", - "score": 0.12117155141304674, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "translation_to", - "metric": "chrf", - "score": 0.4177794744541551, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.24748635254040408, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5863533707100985, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.2588423886300811, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.562682275218684, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "bleu", - "score": 0.23784181416667124, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "translation_to", - "metric": "chrf", - "score": 0.5373128304085978, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.1530279090066045, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.37271468092752974, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.20113161707875454, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.4031608093713332, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "translation_to", - "metric": "chrf", - "score": 0.305586228526799, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.09665585076298037, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.46061627151838797, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.07358577950614774, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.3231011038063018, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "translation_to", - "metric": "chrf", - "score": 0.30653028403316734, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.31954590001023825, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.569897649672018, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.27483441916677864, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6110044168996488, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "bleu", - "score": 0.26585072553894457, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "translation_to", - "metric": "chrf", - "score": 0.6103483251513802, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.3162413313359514, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.2590066624776712, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "translation_to", - "metric": "chrf", - "score": 0.24396774868005255, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.07195213544257117, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.3120035251108586, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.2608300934746321, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "translation_to", - "metric": "chrf", - "score": 0.23931793541759633, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.25267285423995856, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.38987700784253204, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "translation_to", - "metric": "chrf", - "score": 0.23982170773883157, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.10089967636688787, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.4751083796007961, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.40316339131278667, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "translation_to", - "metric": "chrf", - "score": 0.2597280164114605, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.18981964720217231, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.5202248700201121, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.48033951380023887, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "bleu", - "score": 0.05053600948320145, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "translation_to", - "metric": "chrf", - "score": 0.33779456449270456, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.10743641120305437, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.3861534614461426, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.11282878483968255, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.42989143371398053, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "bleu", - "score": 0.1423452551536939, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "translation_to", - "metric": "chrf", - "score": 0.35890833581327075, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.2572958792096885, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.524791117806158, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.42323331934594827, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.5980458552441091, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "bleu", - "score": 0.18643966530029588, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "translation_to", - "metric": "chrf", - "score": 0.472250969694742, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.23051105230450533, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.461339165198002, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.3332932475073326, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.5318071826870329, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "bleu", - "score": 0.12555000630534552, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "translation_to", - "metric": "chrf", - "score": 0.37494030279780705, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.11094349821042929, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.2906910636210368, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.3302669985131613, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "bleu", - "score": 0.10429663629438554, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "translation_to", - "metric": "chrf", - "score": 0.2618510544761293, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.335832686231422, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.2087257243528052, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "translation_to", - "metric": "chrf", - "score": 0.29242900341172495, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.16596275045554132, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.18375130705991488, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "translation_to", - "metric": "chrf", - "score": 0.165036917351539, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.4238185315546578, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.37123872741984293, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "bleu", - "score": 0.05937938635402215, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "translation_to", - "metric": "chrf", - "score": 0.2388282875974679, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.23154237167901778, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5238880458237484, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.24449972325632238, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.5510860378791704, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "bleu", - "score": 0.10987931098593881, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "translation_to", - "metric": "chrf", - "score": 0.35341923833767647, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.2106721715165928, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.3907583551227623, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.2632572840179757, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.5114029284363146, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "bleu", - "score": 0.33060846075951006, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "translation_to", - "metric": "chrf", - "score": 0.4933751565421874, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.13269353024089545, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.44418557281661125, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.11602404900806981, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.4554201930500723, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "bleu", - "score": 0.2209022359029063, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "translation_to", - "metric": "chrf", - "score": 0.486429600270988, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.1997226634456582, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.41104513420673316, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.2428802468105601, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.46168046249055017, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "bleu", - "score": 0.257115532412176, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "translation_to", - "metric": "chrf", - "score": 0.42838270664314443, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.1655577687696921, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.503754492272343, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.2560013421711881, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5334001391869971, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "bleu", - "score": 0.2437911340271475, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "translation_to", - "metric": "chrf", - "score": 0.5216180636484092, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.3516991073654955, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.41790303792506495, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "translation_to", - "metric": "chrf", - "score": 0.25390079010824235, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.011202719508723062, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.0955315433384972, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.39731738011391643, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "bleu", - "score": 0.1297531338447625, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "translation_to", - "metric": "chrf", - "score": 0.41932803455959666, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.10591848049078299, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.49085304041008937, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.36356644720160713, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "translation_to", - "metric": "chrf", - "score": 0.20108339482651794, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.156815032666708, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.23634008457609298, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "translation_to", - "metric": "chrf", - "score": 0.1614830616662192, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.2979511478422567, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.3438754918495763, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "translation_to", - "metric": "chrf", - "score": 0.2895669129947285, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.42338076501360705, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.06874519953789905, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.380714941951927, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "translation_to", - "metric": "chrf", - "score": 0.3207893927453622, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.493823787340623, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.5242768575529999, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "bleu", - "score": 0.06554510293342969, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "translation_to", - "metric": "chrf", - "score": 0.3359614697928464, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.08331902517941604, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.1121490311188424, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "translation_to", - "metric": "chrf", - "score": 0.0636893546858904, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.26613226165653087, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.4704357379534384, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.267579029762668, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.4771565913693486, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "bleu", - "score": 0.18602980983305786, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "translation_to", - "metric": "chrf", - "score": 0.38203825355509946, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2184201291608897, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.24360280654917382, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "bleu", - "score": 0.0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "translation_to", - "metric": "chrf", - "score": 0.2189734700985919, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 0 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 1 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 1 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 2 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 2 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 3 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 3 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 4 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 4 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 5 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 5 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 6 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 7 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 7 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 8 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 8 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "en", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zh", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "es", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ar", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ur", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bn", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pt", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pa", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ru", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sw", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "id", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "de", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ja", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "te", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mr", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "jv", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "openai/gpt-4o-mini", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 1, - "sentence_nr": 9 - }, - { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "vi", - "task": "classification", - "metric": "accuracy", - "score": 0, + "bcp_47": "zh", + "task": "translation_to", + "metric": "bleu", + "score": 0.11254397891886614, "sentence_nr": 9 }, { - "model": "openai/gpt-4o-mini", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, + "model": "meta-llama/llama-4-maverick", + "bcp_47": "zh", + "task": "translation_to", + "metric": "chrf", + "score": 0.20623288988983426, "sentence_nr": 9 }, { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 1, + "model": "meta-llama/llama-3.3-70b-instruct", + "bcp_47": "zh", + "task": "translation_to", + "metric": "bleu", + "score": 0.1100081929352474, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ta", - "task": "classification", - "metric": "accuracy", - "score": 0, + "bcp_47": "zh", + "task": "translation_to", + "metric": "chrf", + "score": 0.18967061672400035, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, + "bcp_47": "hi", + "task": "translation_to", + "metric": "bleu", + "score": 0.27190910124573536, "sentence_nr": 9 }, { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 1, + "model": "openai/gpt-4o-mini", + "bcp_47": "hi", + "task": "translation_to", + "metric": "chrf", + "score": 0.5173567851798608, "sentence_nr": 9 }, { - "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fa", - "task": "classification", - "metric": "accuracy", - "score": 0, + "model": "meta-llama/llama-4-maverick", + "bcp_47": "hi", + "task": "translation_to", + "metric": "bleu", + "score": 0.24493390281390082, "sentence_nr": 9 }, { - "model": "openai/gpt-4o-mini", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, + "model": "meta-llama/llama-4-maverick", + "bcp_47": "hi", + "task": "translation_to", + "metric": "chrf", + "score": 0.48113625107113883, "sentence_nr": 9 }, { - "model": "meta-llama/llama-4-maverick", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 1, + "model": "meta-llama/llama-3.3-70b-instruct", + "bcp_47": "hi", + "task": "translation_to", + "metric": "bleu", + "score": 0.19476681308252697, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "tr", - "task": "classification", - "metric": "accuracy", - "score": 0, + "bcp_47": "hi", + "task": "translation_to", + "metric": "chrf", + "score": 0.42030407727741037, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "yue", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "yue", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yue", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ko", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ko", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ko", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "it", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "it", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "it", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fil", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fil", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fil", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "arz", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "arz", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "arz", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "gu", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "gu", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "gu", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "th", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "th", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "th", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "kn", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "kn", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kn", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ml", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ml", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ml", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "or", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "or", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "or", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "pl", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "pl", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "pl", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ha", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ha", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ha", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sd", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sd", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sd", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ms", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ms", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ms", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "my", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "my", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "my", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "am", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "am", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "am", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "om", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "om", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "om", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "bho", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "bho", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "bho", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "uz", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "uz", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uz", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "az", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "az", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "az", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "su", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "su", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "su", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "nl", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "nl", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "nl", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ary", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ary", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ary", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "uk", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "uk", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "uk", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "yo", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "yo", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "yo", + "bcp_47": "en", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ig", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ig", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ig", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ceb", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ceb", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ceb", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "awa", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, @@ -102263,7 +11821,7 @@ }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "awa", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, @@ -102271,7 +11829,7 @@ }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "awa", + "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, @@ -102279,7 +11837,7 @@ }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mg", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, @@ -102287,15 +11845,15 @@ }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mg", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", - "score": 1, + "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mg", + "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, @@ -102303,7 +11861,7 @@ }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ro", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, @@ -102311,15 +11869,15 @@ }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ro", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", - "score": 0, + "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ro", + "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, @@ -102327,648 +11885,720 @@ }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ne", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ne", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ne", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mai", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mai", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mai", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "as", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "as", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "as", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ny", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ny", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ny", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "so", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "so", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "so", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "mag", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "mag", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "mag", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sr", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sr", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sr", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "si", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "si", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "si", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "km", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "km", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "km", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "hne", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "hne", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hne", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "fuv", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "fuv", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "fuv", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "zu", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "zu", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "zu", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "kk", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "kk", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "kk", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "cs", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "cs", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "cs", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sv", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sv", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sv", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "hu", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "hu", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "hu", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "el", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "el", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "el", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "sn", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "sn", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "sn", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ckb", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ckb", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 1, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ckb", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", - "score": 0, - "sentence_nr": 9 + "score": 1, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "rw", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "rw", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "rw", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 6 + }, + { + "model": "openai/gpt-4o-mini", + "bcp_47": "hi", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 6 + }, + { + "model": "meta-llama/llama-4-maverick", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 6 + }, + { + "model": "meta-llama/llama-3.3-70b-instruct", + "bcp_47": "hi", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "wo", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "wo", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "wo", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "aeb", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "aeb", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "aeb", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ilo", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ilo", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 1, - "sentence_nr": 9 + "score": 0, + "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ilo", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "xh", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 8 + }, + { + "model": "meta-llama/llama-4-maverick", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 8 + }, + { + "model": "meta-llama/llama-3.3-70b-instruct", + "bcp_47": "en", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 8 + }, + { + "model": "openai/gpt-4o-mini", + "bcp_47": "zh", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "xh", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "xh", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 8 + }, + { + "model": "openai/gpt-4o-mini", + "bcp_47": "hi", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 8 + }, + { + "model": "meta-llama/llama-4-maverick", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, - "sentence_nr": 9 + "sentence_nr": 8 + }, + { + "model": "meta-llama/llama-3.3-70b-instruct", + "bcp_47": "hi", + "task": "mmlu", + "metric": "accuracy", + "score": 1, + "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "ti", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "ti", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "ti", - "task": "classification", + "bcp_47": "en", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "be", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "be", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "be", - "task": "classification", + "bcp_47": "zh", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", - "bcp_47": "lua", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", - "bcp_47": "lua", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", - "score": 1, + "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", - "bcp_47": "lua", - "task": "classification", + "bcp_47": "hi", + "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9