Video Question Answering on TIMEScope Short
87.2AccuracyVideo Panels (VideoLLaMA 3 7B)
Evaluation Results
| Method | Links | |
|---|---|---|
| Video Panels (VideoLLaMA 3 7B)#frames=180, Model Context Category=Long-context VLMs2025.09 | 87.2 | |
| VideoLLaMA 3 7B#frames=180, Model Context Category=Long-context VLMs2025.09 | 80.2 | |
| Video Panels (LLaVA-Video 7B)#frames=64, Model Context Category=Medium-context VLMs2025.09 | 79.2 | |
| Video Panels (Qwen-2.5VL 7B)#frames=180, Model Context Category=Long-context VLMs2025.09 | 79.1 | |
| Video Panels (LLaVA-Video 72B)#frames=64, Model Context Category=Medium-context VLMs2025.09 | 75.7 | |
| Qwen-2.5VL 7B#frames=180, Model Context Category=Long-context VLMs2025.09 | 73.9 | |
| Video Panels (Qwen-2VL 7B)#frames=180, Model Context Category=Long-context VLMs2025.09 | 71.2 | |
| Video Panels (LLaVA-OV 72B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 70 | |
| Video Panels (LLaVA-OV 7B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 69.5 | |
| Qwen-2VL 7B#frames=180, Model Context Category=Long-context VLMs2025.09 | 66.1 | |
| LLaVA-Video 72B#frames=64, Model Context Category=Medium-context VLMs2025.09 | 65.4 | |
| LLaVA-Video 7B#frames=64, Model Context Category=Medium-context VLMs2025.09 | 64.8 | |
| Video Panels (Qwen-2.5VL 7B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 60.8 | |
| LLaVA-OV 72B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 59.1 | |
| LLaVA-OV 7B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 58.7 | |
| Video Panels (LLaVA-OV 0.5B)#frames=32, Model Context Category=Medium-context VLMs2025.09 | 56.9 | |
| Qwen-2.5VL 7B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 52.8 | |
| LLaVA-OV 0.5B#frames=32, Model Context Category=Medium-context VLMs2025.09 | 49.4 | |
| Video Panels (Video-LLaVA 7B)#frames=8, Model Context Category=Small-context VLMs2025.09 | 25.6 | |
| Video-LLaVA 7B#frames=8, Model Context Category=Small-context VLMs2025.09 | 24.4 | |
| Video Panels (VideoChat2-HD)#frames=16, Model Context Category=Small-context VLMs2025.09 | 21.3 | |
| VideoChat2-HD#frames=16, Model Context Category=Small-context VLMs2025.09 | 21.2 |