| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| HR-Bench 4K | BVS | Overall Score84.8 | 43 | 17d ago | |
| MMVP | Visual Para-Thinker++ | Accuracy74.9 | 41 | 1mo ago | |
| HR-Bench 8K | BVS | Average Score79.5 | 38 | 18d ago | |
| HRBench 4K | Kimi K2.5 + ETCHR | Pass@186.8 | 26 | 1mo ago | |
| VStarBench | SaGe-3B | Overall Accuracy89 | 19 | 17d ago | |
| V* | Visual Para-Thinker | Accuracy78.8 | 13 | 4mo ago | |
| MMVP (test) | Qwen2.5-VL | MMVP Score75.33 | 11 | 4mo ago | |
| HRBench 8K | Kimi K2.5 + ETCHR | Pass@181.1 | 10 | 2mo ago | |
| V*Bench | Kimi K2.5 + ETCHR | Pass@187.4 | 10 | 2mo ago | |
| AI2D | HEED | Score85.3 | 10 | 2mo ago | |
| InfoVQA | Teacher | Score82.7 | 10 | 2mo ago | |
| TextVQA | HEED | Score83.7 | 10 | 2mo ago | |
| ChartQA | HEED | Score88.6 | 10 | 2mo ago | |
| DocVQA | Teacher | Score95.4 | 10 | 2mo ago | |
| OCRBench v2 | HEED | Score63.9 | 10 | 2mo ago | |
| CV-Bench | Score89.6 | 8 | 1mo ago | ||
| HR-Bench 8K | Score85 | 8 | 1mo ago | ||
| HR-Bench 4K | Score87.9 | 8 | 1mo ago | ||
| EndoAgentBench | EndoCogniAgent | Localization Classification Accuracy75.29 | 8 | 2mo ago | |
| VStarBench | MIRROR(ours) | Score83.77 | 7 | 4mo ago | |
| HRB8K | Qwen2.5-VL-72B | Score77.1 | 7 | 4mo ago | |
| MME-RealWorld Lite | MIRROR(ours) | Score51.49 | 6 | 4mo ago | |
| Fine-grained Perception 6 datasets | HEED | Average Score83.18 | 5 | 2mo ago |