Long-form Video Understanding on LongVideoBench (Original/Filtered Score)
58.4Original ScoreLLaVA-Video
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LLaVA-VideoLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.002025.09 | 58.4 | 49.5 | |
| LLaVA-OneVisionLLM=Qwen2-7B, Use Audio=×, Latency (s)=0.972025.09 | 56.5 | 47.6 | |
| UniMambaMiaLLM=Qwen2-7B, Use Audio=✓, Latency (s)=1.602025.09 | 53.9 | 46.2 | |
| LLaVA-NeXT-Vid.LLM=Vicuna-7B, Use Audio=×, Latency (s)=0.242025.09 | 43.9 | 36.7 | |
| Qwen2-VLLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.632025.09 | 22.9 | 23.1 | |
| Qwen2.5-OmniLLM=Qwen2.5-7B, Use Audio=✓, Latency (s)=4.122025.09 | 22.4 | 21.7 |