Video Question Answering on TIMEScope Long
46.7AccuracyVideo Panels (VideoLLaMA 3 7B)
Evaluation Results
| Method | Links | |
|---|---|---|
| Video Panels (VideoLLaMA 3 7B)#frames=180, Model Context Category=Long-context VLMs2025.09 | 46.7 | |
| Video Panels (LLaVA-Video 7B)#frames=64, Model Context Category=Medium-context VLMs2025.09 | 39.3 | |
| VideoLLaMA 3 7B#frames=180, Model Context Category=Long-context VLMs2025.09 | 39.1 | |
| Qwen-2.5VL 7B#frames=180, Model Context Category=Long-context VLMs2025.09 | 37.6 | |
| Video Panels (Qwen-2.5VL 7B)#frames=180, Model Context Category=Long-context VLMs2025.09 | 35.6 | |
| LLaVA-Video 7B#frames=64, Model Context Category=Medium-context VLMs2025.09 | 34.7 | |
| Video Panels (LLaVA-OV 7B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 33.8 | |
| LLaVA-OV 72B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 33.8 | |
| Video Panels (LLaVA-OV 72B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 32.4 | |
| LLaVA-Video 72B#frames=64, Model Context Category=Medium-context VLMs2025.09 | 30.9 | |
| Video Panels (LLaVA-Video 72B)#frames=64, Model Context Category=Medium-context VLMs2025.09 | 30.9 | |
| LLaVA-OV 7B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 30.2 | |
| Video Panels (LLaVA-OV 0.5B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 30 | |
| Video Panels (Qwen-2.5VL 7B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 30 | |
| Qwen-2.5VL 7B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 28.7 | |
| Video Panels (Qwen-2VL 7B)#frames=180, Model Context Category=Long-context VLMs2025.09 | 26.7 | |
| LLaVA-OV 0.5B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 25.6 | |
| Qwen-2VL 7B#frames=180, Model Context Category=Long-context VLMs2025.09 | 23.8 | |
| VideoChat2-HD#frames=16, Model Context Category=Small-context VLMs2025.09 | 19.8 | |
| Video Panels (VideoChat2-HD)#frames=16, Model Context Category=Small-context VLMs2025.09 | 19.8 | |
| Video-LLaVA 7B#frames=8, Model Context Category=Small-context VLMs2025.09 | 17.6 | |
| Video Panels (Video-LLaVA 7B)#frames=8, Model Context Category=Small-context VLMs2025.09 | 17.1 |