Video Question Answering on NA-VQA (Medium)
63.64ComprehensionClaude Sonnet 4.5
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Claude Sonnet 4.5Type=Proprietary, Use Descr.=true2026.03 | 63.64 | 66.95 | 63.73 | 62.79 | |
| Qwen-235BType=Proprietary, Use Descr.=true2026.03 | 51.29 | 58.11 | 51.37 | 51.48 | |
| GPT-120B OSSType=Proprietary, Use Descr.=true2026.03 | 49.96 | 53.94 | 46.91 | 48.84 | |
| Video-NaRAType=Fine-Tuned Model, Use Descr.=true, Frames=1282026.03 | 36.18 | 38.97 | 34.98 | 34.62 | |
| Video-NaRAType=Zero-Shot VLM, Use Descr.=true, Frames=1282026.03 | 35.92 | 38.33 | 33.69 | 33.36 | |
| Qwen2.5-VLType=Fine-Tuned Model, Frames=1282026.03 | 35.02 | 38.41 | 31.55 | 33.49 | |
| Qwen2.5-VL (7B)Type=Zero-Shot VLM, Frames=1282026.03 | 33.6 | 37.33 | 30.34 | 31.71 | |
| Video-LLaMA3 (7B)Type=Zero-Shot VLM, Frames=1282026.03 | 33 | 36.35 | 28.58 | 30.34 | |
| VideoChat-Flash (7B)Type=Zero-Shot Long-Form VLM, Frames=30002026.03 | 32.87 | 35.15 | 26.26 | 29.44 | |
| InternVL2.5 (7B)Type=Zero-Shot VLM, Frames=642026.03 | 32.19 | 34.46 | 31.85 | 29.44 | |
| MovieChat (7B)Type=Zero-Shot Long-Form VLM, Frames=20482026.03 | 30.85 | 34.24 | 24.54 | 29.22 | |
| LLaVA-OneVision (7B)Type=Zero-Shot VLM, Frames=322026.03 | 30.04 | 33.22 | 24.64 | 25.55 | |
| InternVL2 (7B)Type=Zero-Shot VLM, Frames=322026.03 | 29.96 | 31.29 | 26.82 | 26.82 | |
| VideoChatGPT (7B)Type=Zero-Shot VLM, Frames=1002026.03 | 28.76 | 31.97 | 23.82 | 22.27 | |
| Qwen2.5 Instruct (7B)Type=Zero-Shot VLM, Use Descr.=true2026.03 | 28.5 | 31.93 | 27.3 | 25.58 | |
| VideoLLaVA (7B)Type=Zero-Shot VLM, Frames=82026.03 | 16.57 | 19.61 | 15.67 | 12.45 |