file/result.csv

Model,Model Type,Model Size,Avg. All,Avg. Multi-Choice,Avg. Yes/No,Avg. Caption Matching,Avg. Caption Generation,Action. Multi-Choice,Action. Yes/No,Action. Caption Matching,Action. Caption Generation,Direction. Multi-Choice,Direction. Yes/No,Direction. Caption Matching,Direction. Caption Generation,Speed. Multi-Choice,Speed. Yes/No,Speed. Caption Matching,Speed. Caption Generation,Event Order. Multi-Choice,Event Order. Yes/No,Event Order. Caption Matching,Event Order. Caption Generation,Attribute Change. Multi-Choice,Attribute Change. Yes/No,Attribute Change. Caption Matching,Attribute Change. Caption Generation,Notes
[Video-LLaVA-7B](https://huggingface.co/LanguageBind/Video-LLaVA-7B),VideoLLM,7B,49.77,45.57,56.38,63.34,34.83,76.04,74.32,87.88,50.76,35.22,51.82,53.82,28.67,35.65,50.28,58.42,23.2,37.75,49.21,59.0,38.25,40.97,51.12,58.33,33.59,"answer prompt: ""Please directly give the best option:”"
[VideoChat2-vicuna-stage3](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/scripts/videochat_vicuna/config_7b_stage3.py),VideoLLM,7B,48.81,42.91,58.01,53.69,38.52,76.92,72.8,73.4,54.04,29.55,53.85,51.68,30.96,33.44,53.82,49.48,32.73,35.43,51.31,48.0,34.25,36.81,53.79,45.83,41.41,"answer prompt: ""Please directly give the best option:”"
[LLaMA-VID-7B-short-video](https://huggingface.co/YanweiLi/llama-vid-7b-full-224-video-fps-1),VideoLLM,7B,45.61,38.04,52.96,56.02,34.78,61.24,63.01,73.4,53.03,29.85,48.79,50.46,27.98,29.65,49.16,51.2,21.91,33.77,48.43,53.67,35.5,34.03,52.68,51.74,35.94,"answer prompt: ""Please directly give the best option:”"
[mPLUG-Owl-video](https://huggingface.co/MAGAer13/mplug-owl-llama-7b-video),VideoLLM,7B,44.15,36.39,54.42,48.5,34.43,55.92,64.36,57.24,46.46,32.24,50.61,41.9,28.21,31.55,51.21,43.64,30.41,27.48,51.31,48.67,31.25,32.99,52.01,51.74,36.46,"answer prompt: ""Please directly give the best option:”"
[PandaGPT-13B-maxlen-400](https://huggingface.co/openllmplayground/pandagpt_13b_max_len_400),VideoLLM,13B,41.64,34.37,51.81,51.56,27.5,36.69,53.04,49.16,23.74,34.03,49.6,55.96,25.69,33.75,50.84,49.48,26.03,32.12,53.66,54.33,29.75,35.07,52.23,48.26,32.55,"answer prompt: ""Please directly give the best option:”"
[Valley2-7B](https://huggingface.co/luoruipu1/Valley2-7b),VideoLLM,7B,37.49,29.56,53.49,34.6,26.35,43.49,58.11,36.7,24.75,29.55,52.02,33.64,20.41,24.92,52.51,36.77,21.91,18.54,50.26,36.0,35.75,29.86,52.9,29.86,29.43,"answer prompt: ""Please directly give the best option:”"
[Video-ChatGPT](https://github.com/mbzuai-oryx/Video-ChatGPT),VideoLLM,7B,43.54,37.66,50.67,53.69,31.84,61.54,52.53,69.02,40.91,28.96,50.0,49.24,28.44,29.02,49.53,47.42,24.48,36.09,51.05,52.67,31.75,30.9,50.0,50.35,33.85,"answer prompt: ""Please directly give the best option:”"
[Video-LLaMA-2-13B](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Finetuned),VideoLLM,13B,43.4,31.27,53.73,54.16,32.24,52.07,68.07,70.71,54.29,25.07,45.95,45.26,21.33,28.08,48.79,56.01,13.92,26.82,51.83,52.0,38.5,22.22,50.89,47.57,33.85,"answer prompt: ""Please directly give the best option:”"
Gemini-1.5-pro,VideoLLM,-,67.1,63.92,70.32,77.45,57.88,96.75,88.18,97.98,87.88,43.28,54.45,63.0,36.7,55.21,63.87,65.64,38.14,55.63,68.85,81.0,55.25,67.71,73.21,80.9,73.7,"answer prompt: ""Please directly give the best option:”"
[LLaVA-1.5-13B](https://huggingface.co/liuhaotian/llava-v1.5-13b),ImageLLM,13B,51.3,47.41,56.38,64.27,38.42,85.5,74.66,92.59,67.42,31.04,48.79,57.49,31.88,40.06,48.98,58.76,24.74,35.43,49.48,59.0,33.0,42.36,55.36,53.82,35.42,"answer prompt: ""Please directly give the best option:”"
[SPHINX-v2](https://huggingface.co/Alpha-VLLM/LLaMA2-Accessory/tree/main/finetune/mm/SPHINX/SPHINX-v2-1k),ImageLLM,13B,51.92,50.63,59.07,64.34,34.88,89.94,79.05,93.27,67.93,36.72,51.21,55.96,19.04,43.53,54.75,54.3,20.36,37.42,54.45,59.67,37.25,42.36,50.45,59.03,30.99,"answer prompt: ""Please directly give the best option:”"
[Qwen-VL-Chat](https://huggingface.co/Qwen/Qwen-VL-Chat),ImageLLM,7B,52.9,51.08,60.01,64.07,37.28,88.46,81.42,91.58,62.63,37.01,51.62,54.13,27.75,41.32,59.78,54.98,29.64,41.39,50.79,63.67,34.75,44.44,49.11,56.6,32.29,"answer prompt: ""Please directly give the best option:”"
[Reka-Core-20240501](https://docs.reka.ai/image-video-and-audio-chat),VideoLLM,-,64.31,61.08,65.14,74.05,58.53,96.15,90.71,97.31,91.41,40.9,52.83,58.1,36.47,49.21,54.0,63.92,47.42,57.28,57.33,81.0,61.25,60.42,64.96,71.18,58.07,
[LLaVA-NeXT-Video-32B-Qwen](https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-32B-Qwen),VideoLLM,32B,66.74,68.67,69.38,76.51,54.64,95.86,86.82,96.3,85.86,42.09,54.05,59.02,30.28,49.53,57.73,62.54,27.32,78.48,74.35,89.0,65.75,78.47,72.99,77.08,66.15,32 frames
[LLaVA-NeXT-Video-7B-DPO](https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-7B-DPO),VideoLLM,7B,53.75,50.57,61.19,63.01,40.22,87.57,83.78,92.59,63.38,35.82,51.42,54.74,32.8,41.32,56.42,55.33,27.06,39.74,54.97,56.0,39.5,45.83,53.12,56.94,38.8,32 frames
[LongVA-7B](https://huggingface.co/lmms-lab/LongVA-7B),VideoLLM,7B,56.95,56.14,62.13,65.67,44.71,92.31,86.15,94.61,75.76,36.72,50.4,54.43,35.32,43.22,53.07,53.26,32.22,54.3,61.78,64.33,35.25,52.43,54.46,62.5,45.83,32 frames
[Llama-3-VILA1.5-8B](https://huggingface.co/Efficient-Large-Model/Llama-3-VILA1.5-8B),VideoLLM,8B,58.79,56.39,63.64,68.93,47.16,92.9,84.8,94.95,74.75,33.73,52.23,58.72,36.24,44.16,54.38,60.48,31.7,50.0,61.26,66.0,46.75,60.07,61.38,65.28,47.14,8 frames