Benchmark
LVBench
vision
multimodal
long_context
multimodal
LVBench is an extreme long video understanding benchmark designed to evaluate multimodal models on videos up to two hours in duration. It contains 6 major categories and 21 subcategories, with videos averaging five times longer than existing datasets. The benchmark addresses applications requiring comprehension of extremely long videos.
语言EN
满分1
参评模型5
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Qwen2.5 VL 32B Instruct | Alibaba Cloud / Qwen Team | 49.0 | 来源 ↗ |
| 2 | Qwen2.5 VL 72B Instruct | Alibaba Cloud / Qwen Team | 47.3 | 来源 ↗ |
| 3 | Qwen2.5 VL 7B Instruct | Alibaba Cloud / Qwen Team | 45.3 | 来源 ↗ |
| 4 | Nova Pro | Amazon | 41.6 | 来源 ↗ |
| 5 | Nova Lite | Amazon | 40.4 | 来源 ↗ |