Multimodal Video Understanding on MMMU Video
48.8Original ScoreQwen2.5-Omni
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-OmniLLM=Qwen2.5-7B, Use Audio=✓, Latency (s)=4.122025.09 | 48.8 | 37.2 | |
| LLaVA-VideoLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.002025.09 | 38.3 | 31 | |
| UniMambaMiaLLM=Qwen2-7B, Use Audio=✓, Latency (s)=1.602025.09 | 36.7 | 29.3 | |
| LLaVA-OneVisionLLM=Qwen2-7B, Use Audio=×, Latency (s)=0.972025.09 | 33.1 | 25.7 | |
| Qwen2-VLLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.632025.09 | 32.9 | 24.2 | |
| LLaVA-NeXT-Vid.LLM=Vicuna-7B, Use Audio=×, Latency (s)=0.242025.09 | 16.3 | 14.1 |