Spaces:
Running
Running
{"Models": "UNITE-Instruct-7B","Model Size(B)": 8.29,"Data Source": "Self-Reported","V2-Overall":null,"V1-Overall": 70.3,"I-CLS": 68.3,"I-QA": 65.1,"I-RET": 71.6,"I-VG": 84.8,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL": "https://huggingface.co/friedrichor/Unite-Instruct-Qwen2-VL-7B"} | |
{"Models": "UNITE-Instruct-2B","Model Size(B)": 2.21,"Data Source": "Self-Reported","V2-Overall":null,"V1-Overall": 63.3,"I-CLS": 63.2,"I-QA": 55.9,"I-RET": 65.4,"I-VG": 75.6,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL": "https://huggingface.co/friedrichor/Unite-Instruct-Qwen2-VL-2B"} | |
{"Models":"interestFM-UIR-CAFe-0.5B","Model Size(B)":0.894,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":59.6,"I-CLS":59.1,"I-QA":49.1,"I-RET":61.0,"I-VG":83.0,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/arxiv.org\/pdf\/2503.19900"} | |
{"Models":"interestFM-UIR-CAFe-7B","Model Size(B)":8.03,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":69.8,"I-CLS":65.2,"I-QA":65.6,"I-RET":70.0,"I-VG":91.2,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/arxiv.org\/pdf\/2503.19900"} | |
{"Models":"BGE-VL-v1.5 (zeroshot; LlaVA-1.6-Mistral)","Model Size(B)":7.57,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":60.1,"I-CLS":56.1,"I-QA":55.3,"I-RET":63.9,"I-VG":70.8,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/BAAI\/BGE-VL-v1.5-zs"} | |
{"Models":"BGE-VL-v1.5 (FT; LlaVA-1.6-Mistral)","Model Size(B)":7.57,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":69.4,"I-CLS":63.7,"I-QA":64.9,"I-RET":72.2,"I-VG":86.6,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https://huggingface.co/BAAI/BGE-VL-v1.5-mmeb"} | |
{"Models":"B3_Qwen2_7B","Model Size(B)":8.29,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":72.0,"I-CLS":70.0,"I-QA":66.5,"I-RET":74.1,"I-VG":84.6,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/raghavlite\/B3_Qwen2_7B"} | |
{"Models":"B3_Qwen2_2B","Model Size(B)":2.21,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":68.1,"I-CLS":67.0,"I-QA":61.19,"I-RET":70.85,"I-VG":79.88,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/raghavlite\/B3_Qwen2_2B"} | |
{"Models":"CLIP-FT","Model Size(B)":0.428,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":45.4,"I-CLS":55.2,"I-QA":19.7,"I-RET":53.2,"I-VG":62.2,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/doi.org\/10.48550\/arXiv.2103.00020"} | |
{"Models":"LLaVE-0.5B","Model Size(B)":0.894,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":59.1,"I-CLS":57.4,"I-QA":50.3,"I-RET":59.8,"I-VG":82.9,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/zhibinlan\/LLaVE-0.5B"} | |
{"Models":"LLaVE-2B","Model Size(B)":1.95,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":65.2,"I-CLS":62.1,"I-QA":60.2,"I-RET":65.2,"I-VG":84.9,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/zhibinlan\/LLaVE-2B"} | |
{"Models":"LLaVE-7B","Model Size(B)":8.03,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":70.3,"I-CLS":65.7,"I-QA":65.4,"I-RET":70.9,"I-VG":91.9,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/zhibinlan\/LLaVE-7B"} | |
{"Models":"MM-Embed","Model Size(B)":8.18,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":50.0,"I-CLS":48.1,"I-QA":32.3,"I-RET":63.8,"I-VG":57.8,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/nvidia\/MM-Embed"} | |
{"Models":"MMRet-MLLM (FT)","Model Size(B)":7.57,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":64.1,"I-CLS":56.0,"I-QA":57.4,"I-RET":69.9,"I-VG":83.6,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/JUNJIE99\/MMRet-large"} | |
{"Models":"MMRet-MLLM (LLaVA-1.6)","Model Size(B)":7.57,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":44.0,"I-CLS":47.2,"I-QA":18.4,"I-RET":56.5,"I-VG":62.2,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/JUNJIE99\/MMRet-large"} | |
{"Models":"Magiclens","Model Size(B)":0.428,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":27.8,"I-CLS":38.8,"I-QA":8.3,"I-RET":35.4,"I-VG":26.0,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/github.com\/google-deepmind\/magiclens"} | |
{"Models":"OpenCLIP-FT","Model Size(B)":0.428,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":47.2,"I-CLS":56.0,"I-QA":21.9,"I-RET":55.4,"I-VG":64.1,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/doi.org\/10.48550\/arXiv.2212.07143"} | |
{"Models":"QQMM-embed","Model Size(B)":8.297,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":72.175,"I-CLS":70.07,"I-QA":69.52,"I-RET":71.175,"I-VG":87.075,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/github.com\/QQ-MM\/QQMM-embed"} | |
{"Models":"UniIR (BLIP_FF)","Model Size(B)":0.247,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":42.8,"I-CLS":42.1,"I-QA":15.0,"I-RET":60.1,"I-VG":62.2,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/UniIR"} | |
{"Models":"UniIR (CLIP_SF)","Model Size(B)":0.428,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":44.7,"I-CLS":44.3,"I-QA":16.2,"I-RET":61.8,"I-VG":65.3,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/UniIR"} | |
{"Models":"UniME(LLaVA-1.6-7B-LoRA-LowRes)","Model Size(B)":7.57,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":66.6,"I-CLS":60.6,"I-QA":52.9,"I-RET":67.9,"I-VG":85.1,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/DeepGlint-AI\/UniME-LLaVA-1.6-7B"} | |
{"Models":"UniME(LLaVA-OneVision-7B-LoRA-Res336)","Model Size(B)":8.03,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":70.7,"I-CLS":66.8,"I-QA":66.6,"I-RET":70.5,"I-VG":90.9,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/DeepGlint-AI\/UniME-LLaVA-OneVision-7B"} | |
{"Models":"UniME(Phi-3.5-V-LoRA)","Model Size(B)":4.2,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":64.2,"I-CLS":54.8,"I-QA":55.9,"I-RET":64.5,"I-VG":81.8,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/DeepGlint-AI\/UniME-Phi3.5-V-4.2B"} | |
{"Models":"VLM2Vec (LLaVA-1.6-LoRA-HighRes)","Model Size(B)":7.57,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":62.9,"I-CLS":61.2,"I-QA":49.9,"I-RET":67.4,"I-VG":86.1,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-LLaVa-Next"} | |
{"Models":"VLM2Vec (LLaVA-1.6-LoRA-LowRes)","Model Size(B)":7.57,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":55.0,"I-CLS":54.7,"I-QA":50.3,"I-RET":56.2,"I-VG":64.0,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-LLaVa-Next"} | |
{"Models":"VLM2Vec (Phi-3.5-V-FT)","Model Size(B)":4.15,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":55.9,"I-CLS":52.8,"I-QA":50.3,"I-RET":57.8,"I-VG":72.3,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Full"} | |
{"Models":"VLM2Vec (Phi-3.5-V-LoRA)","Model Size(B)":4.15,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":60.1,"I-CLS":54.8,"I-QA":54.9,"I-RET":62.3,"I-VG":79.5,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Full"} | |
{"Models":"VLM2Vec (Qwen2-VL-2B-LoRA-HighRes)","Model Size(B)":2.21,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":59.3,"I-CLS":59.0,"I-QA":49.4,"I-RET":65.4,"I-VG":73.4,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Qwen2VL-2B"} | |
{"Models":"VLM2Vec (Qwen2-VL-7B-LoRA-HighRes)","Model Size(B)":8.29,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":65.8,"I-CLS":62.6,"I-QA":57.8,"I-RET":69.9,"I-VG":81.7,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Qwen2VL-7B"} | |
{"Models":"blip2-opt-2.7b","Model Size(B)":3.74,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":25.2,"I-CLS":27.0,"I-QA":4.2,"I-RET":33.9,"I-VG":47.0,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/Salesforce\/blip2-opt-2.7b"} | |
{"Models":"clip-vit-large-patch14","Model Size(B)":0.428,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":37.8,"I-CLS":42.8,"I-QA":9.1,"I-RET":53.0,"I-VG":51.8,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/openai\/clip-vit-large-patch14"} | |
{"Models":"e5-v","Model Size(B)":8.36,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":13.3,"I-CLS":21.8,"I-QA":4.9,"I-RET":11.5,"I-VG":19.0,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/royokong\/e5-v"} | |
{"Models":"gme-Qwen2-VL-2B-Instruct","Model Size(B)":2.21,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":55.8,"I-CLS":56.9,"I-QA":41.2,"I-RET":67.8,"I-VG":53.4,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/Alibaba-NLP\/gme-Qwen2-VL-2B-Instruct"} | |
{"Models":"mmE5 (w\/ 560K synthetic data)","Model Size(B)":10.6,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":58.6,"I-CLS":60.6,"I-QA":55.7,"I-RET":54.7,"I-VG":72.4,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/intfloat\/mmE5-mllama-11b-instruct"} | |
{"Models":"mmE5-mllama-11b-instruct","Model Size(B)":10.6,"Data Source":"Self-Reported","V2-Overall":null,"V1-Overall":69.8,"I-CLS":67.6,"I-QA":62.6,"I-RET":71.0,"I-VG":89.6,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/intfloat\/mmE5-mllama-11b-instruct"} | |
{"Models":"open_clip-ViT-L\/14","Model Size(B)":0.428,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":39.7,"I-CLS":47.8,"I-QA":10.9,"I-RET":52.3,"I-VG":53.3,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/github.com\/mlfoundations\/open_clip"} | |
{"Models":"siglip-base-patch16-224","Model Size(B)":0.203,"Data Source":"TIGER-Lab","V2-Overall":null,"V1-Overall":34.8,"I-CLS":40.3,"I-QA":8.4,"I-RET":31.6,"I-VG":59.5,"V-CLS":null,"V-QA":null,"V-RET":null,"V-MRET":null,"VisDoc":null,"URL":"https:\/\/huggingface.co\/google\/siglip-base-patch16-224"} | |