| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TRICKME | VANILLA-VERB | Accuracy53.88 | 20 | 4d ago | |
| GRACE | VANILLA-VERB | Accuracy48.27 | 20 | 4d ago | |
| GUESS | VANILLA-VERB | Accuracy0.1858 | 20 | 4d ago | |
| 20Q | VANILLA-VERB | Accuracy33.87 | 20 | 4d ago | |
| VECBench OOD VER | EmoCaliber | ECE0.1217 | 13 | 4d ago | |
| VECBench ID VSA | Qwen3-VL | ECE0.37 | 13 | 4d ago | |
| VECBench ID VER | EmoCaliber | ECE13.63 | 13 | 4d ago | |
| MediTOD | MedConf | AUROC68.7 | 7 | 4d ago | |
| DDXPlus | MedConf | AUROC0.795 | 7 | 4d ago | |
| VSR (test) | Vision-based confidence estimation framework | AUROC67.4 | 6 | 4d ago | |
| MedQA (test) | MedConf | AUROC0.69 | 3 | 4d ago |