Video Question Answering on EG-VQA (test)
45.68Strict Acc (Desc.)Human Results*
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Human Results*2026.06 | 45.68 | 23.87 | 58.93 | 46.73 | 45.44 | 62.39 | 51.47 | 78.56 | 59.72 | 65.83 | |
| GPT-4oModel Category=Commercial Large Multimodal Models2026.06 | 18.9 | 23.08 | 37.2 | 35.1 | 28.47 | 40.1 | 38.94 | 48 | 53.5 | 45.05 | |
| Gemini-2.5-FlashModel Category=Commercial Large Multimodal Models2026.06 | 14.58 | 20.45 | 33.93 | 28.89 | 24.87 | 37.5 | 36.36 | 43.75 | 46.67 | 41.19 | |
| EG-ReasonerBase Model=Qwen2.5-VL-7B-Instruct2026.06 | 14.2 | 10.92 | 33.16 | 48.16 | 26.88 | 34.12 | 27.1 | 48.46 | 60.5 | 42.71 | |
| VideoChat-R1-7BModel Category=Open-sourced Video-LLMs2026.06 | 13.24 | 9.99 | 24.1 | 19.81 | 16.87 | 30.29 | 22.9 | 41.37 | 34.15 | 32.21 | |
| TW-GRPOModel Category=Open-sourced Video-LLMs2026.06 | 12.37 | 7.48 | 25.8 | 24.21 | 17.58 | 27.79 | 19.56 | 39.97 | 36.7 | 31.14 | |
| VideoChat-R1.5-7BModel Category=Open-sourced Video-LLMs2026.06 | 10.65 | 8.12 | 22.92 | 19.02 | 15.29 | 28.46 | 22.04 | 39.01 | 32.01 | 30.42 | |
| Time-R1-7BModel Category=Open-sourced Video-LLMs2026.06 | 10.52 | 7.74 | 22.73 | 21.15 | 15.66 | 27.52 | 20.49 | 39.24 | 34.24 | 30.44 | |
| Qwen2.5-VL-7BModel Category=Open-sourced Video-LLMs2026.06 | 9.91 | 7.73 | 22.36 | 16.8 | 14.31 | 24.96 | 20.07 | 36.21 | 30.3 | 27.96 | |
| VideoChat-R1-Thinking-7BModel Category=Open-sourced Video-LLMs2026.06 | 9.91 | 8.4 | 24.5 | 25.65 | 17.29 | 26.75 | 20.97 | 40.09 | 38.74 | 31.76 | |
| InternVL-3-8BModel Category=Open-sourced Video-LLMs2026.06 | 9.71 | 5.24 | 18.11 | 13.64 | 11.71 | 27.91 | 18.75 | 36.45 | 28.72 | 26.36 |