David Pomerenke
commited on
Commit
·
be99aac
1
Parent(s):
4973af4
Update README
Browse files
README.md
CHANGED
|
@@ -8,12 +8,14 @@ license: cc-by-sa-4.0
|
|
| 8 |
short_description: Evaluating LLM performance across all human languages.
|
| 9 |
datasets:
|
| 10 |
- openlanguagedata/flores_plus
|
|
|
|
| 11 |
- mozilla-foundation/common_voice_1_0
|
| 12 |
models:
|
| 13 |
- meta-llama/Llama-3.3-70B-Instruct
|
| 14 |
- mistralai/Mistral-Small-24B-Instruct-2501
|
| 15 |
- deepseek-ai/DeepSeek-V3
|
| 16 |
- microsoft/phi-4
|
|
|
|
| 17 |
tags:
|
| 18 |
- leaderboard
|
| 19 |
- submission:manual
|
|
@@ -36,11 +38,3 @@ For tag meaning, see https://huggingface.co/spaces/leaderboards/LeaderboardsExpl
|
|
| 36 |
# AI Language Monitor 🌍
|
| 37 |
|
| 38 |
Benchmarking all big AI models on all benchmarkable languages.
|
| 39 |
-
|
| 40 |
-
Sources:
|
| 41 |
-
|
| 42 |
-
1. For AI models: [OpenRouter](https://openrouter.ai/)
|
| 43 |
-
2. For language benchmarks: [FLORES+](https://github.com/openlanguagedata/flores)
|
| 44 |
-
3. For language statistics: [Wikidata](https://gist.github.com/unhammer/3e8f2e0f79972bf5008a4c970081502d), [Ethnologue](https://www.ethnologue.com/browse/names/)
|
| 45 |
-
|
| 46 |
-
[UI sketch](https://www.tldraw.com/ro/5YkWi9dfBixOkQ4FV23zA?d=v192.-1.2090.1569.page)
|
|
|
|
| 8 |
short_description: Evaluating LLM performance across all human languages.
|
| 9 |
datasets:
|
| 10 |
- openlanguagedata/flores_plus
|
| 11 |
+
- google/fleurs
|
| 12 |
- mozilla-foundation/common_voice_1_0
|
| 13 |
models:
|
| 14 |
- meta-llama/Llama-3.3-70B-Instruct
|
| 15 |
- mistralai/Mistral-Small-24B-Instruct-2501
|
| 16 |
- deepseek-ai/DeepSeek-V3
|
| 17 |
- microsoft/phi-4
|
| 18 |
+
- openai/whisper-large-v3
|
| 19 |
tags:
|
| 20 |
- leaderboard
|
| 21 |
- submission:manual
|
|
|
|
| 38 |
# AI Language Monitor 🌍
|
| 39 |
|
| 40 |
Benchmarking all big AI models on all benchmarkable languages.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|