| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| RealWorldQA | DAPO | Accuracy71.3 | 64 | 1mo ago | |
| MMMU | Accuracy75.1 | 35 | 2mo ago | ||
| VisNumBench | Vision-SR1 | Accuracy44.6 | 30 | 2mo ago | |
| MMMU Pro | PDCR | Accuracy50.7 | 30 | 2mo ago | |
| SeedBench 2+ | DPA-Qwen3-32B | SeedBench2+ Score67.7 | 11 | 2mo ago | |
| General Visual Benchmarks RealWorldQA, MMStar | RealWorldQA Score71.3 | 7 | 26d ago | ||
| ScienceQA | IREASONER | Accuracy89.92 | 6 | 5mo ago | |
| AI2D | IREASONER | Accuracy83.89 | 6 | 5mo ago | |
| InfoGraphic-VQA (val) | IREASONER | Accuracy81.56 | 6 | 5mo ago | |
| 10-benchmark Global Set | HEED | Average Score78.79 | 5 | 2mo ago | |
| SQA | Unicorn | SQA Score68.81 | 4 | 1mo ago | |
| MME | Unicorn | MME Score60.24 | 4 | 1mo ago | |
| V*Bench | DCRL | Overall Score85.9 | 2 | 1mo ago | |
| MME-RealWorld | DCRL | Score63.8 | 2 | 1mo ago |