Video Question Answering on NA-VQA (Overall)
62.15Average ScoreClaude Sonnet 4.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude Sonnet 4.5Type=Proprietary, Use Descr.=true2026.03 | 62.15 | |
| Qwen-235BType=Proprietary, Use Descr.=true2026.03 | 51.28 | |
| GPT-120B OSSType=Proprietary, Use Descr.=true2026.03 | 49.38 | |
| Video-NaRAType=Fine-Tuned Model, Use Descr.=true, Frames=1282026.03 | 35.74 | |
| Video-NaRAType=Zero-Shot VLM, Use Descr.=true, Frames=1282026.03 | 34.88 | |
| Qwen2.5-VLType=Fine-Tuned Model, Frames=1282026.03 | 33.79 | |
| Qwen2.5-VL (7B)Type=Zero-Shot VLM, Frames=1282026.03 | 33.18 | |
| Video-LLaMA3 (7B)Type=Zero-Shot VLM, Frames=1282026.03 | 32.83 | |
| InternVL2.5 (7B)Type=Zero-Shot VLM, Frames=642026.03 | 31.96 | |
| VideoChat-Flash (7B)Type=Zero-Shot Long-Form VLM, Frames=30002026.03 | 30.31 | |
| MovieChat (7B)Type=Zero-Shot Long-Form VLM, Frames=20482026.03 | 29.98 | |
| LLaVA-OneVision (7B)Type=Zero-Shot VLM, Frames=322026.03 | 28.5 | |
| InternVL2 (7B)Type=Zero-Shot VLM, Frames=322026.03 | 28.38 | |
| Qwen2.5 Instruct (7B)Type=Zero-Shot VLM, Use Descr.=true2026.03 | 26.74 | |
| VideoChatGPT (7B)Type=Zero-Shot VLM, Frames=1002026.03 | 26.28 | |
| VideoLLaVA (7B)Type=Zero-Shot VLM, Frames=82026.03 | 16.3 |