Video Question Answering on MLVU 1.0 (test)
68.5AccuracyLLaVA-OV-7B + ReKV
Evaluation results
| Method | Links | |
|---|---|---|
| LLaVA-OV-7B + ReKVFrames/FPS=0.5 fps, # Mem. Tok=5.9K2026.05 | 68.5 | |
| MiMo-VL-7B + TCS#Frames=322026.01 | 67.8 | |
| LLaVA-OV-7B + MuKVFrames/FPS=0.5fps, # Mem. Tok=5.9K2026.05 | 67.8 | |
| LongVUFrames/FPS=400/1fps2026.05 | 67.6 | |
| LLaVA-OV-7B + StreamMemFrames/FPS=0.5/0.2 fps, # Mem. Tok=6K2026.05 | 66.9 | |
| LLaVA-OV-7B + LiveVLMFrames/FPS=0.5/0.2 fps2026.05 | 66.3 | |
| Qwen3-VL-4B + MuKVFrames/FPS=0.5fps, # Mem. Tok=5.9K2026.05 | 66 | |
| Qwen2-VL-7B + Q-Frame#Frames=4+8+322026.01 | 65.4 | |
| Qwen3-VL-2B + MuKVFrames/FPS=0.5fps, # Mem. Tok=5.9K2026.05 | 65.2 | |
| Video-XL-7B#Frames=1282026.01 | 64.9 | |
| Qwen3-VL-4BFrames/FPS=7682026.05 | 64.8 | |
| LLaVA-OV-7BFrames/FPS=322026.05 | 64.7 | |
| GPT-4o2026.05 | 64.6 | |
| Qwen3-VL-2BFrames/FPS=7682026.05 | 64 | |
| Qwen2.5-VL-3BFrames/FPS=7682026.05 | 63.3 | |
| Qwen2.5-VL-3B + MuKVFrames/FPS=0.5 fps, # Mem. Tok=5.9K2026.05 | 63 | |
| Qwen2.5-VL-3B + StreamMemFrames/FPS=4.0/0.5 fps, # Mem. Tok=6K2026.05 | 62.3 | |
| Qwen2.5-VL-3B + InfiniPot-VFrames/FPS=768, # Mem. Tok=6K2026.05 | 62.1 | |
| DispiderFPS=1 fps2026.05 | 61.7 | |
| Qwen2-VL-7B + TCS#Frames=322026.01 | 61.2 | |
| MiMo-VL-7B#Frames=322026.01 | 60.9 | |
| Qwen2-VL-7B#Frames=322026.01 | 58.1 | |
| LLaVA-OV-0.5B + MuKVFrames/FPS=0.5fps, # Mem. Tok=5.9K2026.05 | 55.2 | |
| LLaVA-OV-0.5B + ReKVFrames/FPS=0.5 fps, # Mem. Tok=5.9K2026.05 | 53.2 | |
| LLaVA-OV-0.5BFrames/FPS=322026.05 | 50.4 | |
| MovieChat+Frames=20482026.05 | 25.8 |