| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Image Implication True-False 1.0 (test) | MetaphorStar-32B | Accuracy74 | 25 | 3mo ago | |
| MIMIC | Task Utility77.78 | 20 | 22d ago | ||
| IU-XRay | Task Utility95.92 | 20 | 22d ago | ||
| TMQA | T3LLM | Accuracy0.766 | 8 | 3mo ago | |
| PBSBench Slide-level 1.0 (test) | PBS-VL | Accuracy86 | 6 | 1mo ago |