| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMVet | Bee-8B | Score83.9 | 63 | 2mo ago | |
| MMStar | Accuracy80.1 | 51 | 23d ago | ||
| HallusionBench | Accuracy73.48 | 20 | 2mo ago | ||
| MME | VQA Score2,397 | 19 | 1mo ago | ||
| RWQA pt-PT | Accuracy64.7 | 16 | 1mo ago | ||
| POPE pt-PT | AMALIA-VL | Accuracy89.6 | 16 | 1mo ago | |
| SEED pt-PT | Accuracy78.5 | 16 | 1mo ago | ||
| MMPro pt-PT | InternVL3.5-8B | Accuracy38 | 16 | 1mo ago | |
| MMStar pt-PT | LLaVA-OV1.5-8B | Accuracy64.7 | 16 | 1mo ago | |
| MMMU pt-PT | InternVL3.5-8B | Accuracy53.7 | 16 | 1mo ago | |
| MME pt-PT | Qwen3-VL-8B | Score2,355 | 16 | 1mo ago | |
| MMMU (val) | Ours (CDRL + CA-TTS) | Score59.9 | 15 | 4mo ago | |
| MMBench en (dev) | Accuracy90.3 | 15 | 1mo ago | ||
| POPE | Molmo | Accuracy89 | 14 | 3mo ago | |
| HRBench | Accuracy78.5 | 14 | 4mo ago | ||
| GUIChat | Accuracy93.14 | 14 | 4mo ago | ||
| CountBench | Accuracy97.35 | 10 | 4mo ago | ||
| VisuLogic | SegAnswer | Score27.1 | 9 | 17d ago | |
| MMStar (test) | Ours (CDRL + CA-TTS) | Overall Accuracy71.3 | 8 | 4mo ago | |
| ViVerBench | Seed2.0 Lite | Pass@180 | 7 | 23d ago | |
| VibeEval | Seed2.0 Pro | Pass@181.4 | 7 | 23d ago | |
| WorldVQA | Seed2.0 Pro | Pass@149.9 | 7 | 23d ago | |
| MTVQA | Pass@153.1 | 7 | 23d ago | ||
| MUIRBench | Seed2.0 Pro | Pass@181.8 | 7 | 23d ago | |
| MMStar | Pass@183.1 | 7 | 23d ago |