| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MVBench | LLaVA-Video-7B | Accuracy100 | 635 | 18d ago | |
| VideoMME | Gemini-1.5-Pro | Score (Overall)75 | 369 | 24d ago | |
| MLVU | Score78.19 | 233 | 18d ago | ||
| VideoMME | Overall Score100 | 222 | 2mo ago | ||
| MVBench (test) | FSR | Accuracy100.3 | 201 | 1mo ago | |
| EgoSchema | FLoC | EgoSchema Score69.4 | 185 | 1mo ago | |
| MLVU | RETOOL-VIDEO | Accuracy81.5 | 147 | 1mo ago | |
| Video-MME without subtitles | Overall Score84.8 | 145 | 16d ago | ||
| LongVideoBench | VSI-DETECTOR | Accuracy73.89 | 128 | 18d ago | |
| LVB | FLoC | Accuracy66.49 | 101 | 1mo ago | |
| Video-MME | HiMu | Overall Score78.18 | 96 | 4mo ago | |
| LVBench | SCORE | Overall Accuracy102.8 | 95 | 18d ago | |
| Video-MME | Overall Score78.78 | 92 | 3mo ago | ||
| MMVU | Seed2.0 Pro | Accuracy78.2 | 91 | 18d ago | |
| Video-MME | Gemini-2.5 Pro | Accuracy84.8 | 90 | 22d ago | |
| LongVideoBench, MLVU, and VideoMME Aggregate | InternVL3-8B + LiteFrame | Average Score65.7 | 84 | 2mo ago | |
| MLVU | Accuracy87.34 | 80 | 4mo ago | ||
| VideoMME | VisReflect | Accuracy (No Subtitles)67.4 | 67 | 25d ago | |
| VideoMMMU | Accuracy68.64 | 67 | 18d ago | ||
| Aggregate MVBench, LongVideo Bench, MLVU, VideoMME | Qwen3-VL-8B-Instruct | Average Accuracy100 | 63 | 2mo ago | |
| LongVideoBench | GPT-4o | Accuracy66.7 | 59 | 24d ago | |
| MSRVTT | CDPruner | Acc57.7 | 57 | 1mo ago | |
| Video-MME v1.0 (test) | TS-LLaVA | Score (Short)72.4 | 56 | 4mo ago | |
| TGIF | Accuracy51.4 | 56 | 1mo ago | ||
| TempCompass MCQ (test) | Accuracy82.8 | 55 | 3mo ago |