| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Vad-Reasoning-Plus | Vad-R1-Plus | MCQ Score96.4 | 27 | 4d ago | |
| MMLU professional medicine | GPT-4o | Accuracy94 | 21 | 4d ago | |
| C3 | GRASP | Accuracy44.6 | 8 | 4d ago | |
| M3GIA | Accuracy59.8 | 5 | 4d ago | ||
| MMBench (test dev) | Accuracy86.4 | 5 | 4d ago | ||
| SEED-IMG | Accuracy76.5 | 4 | 4d ago |