| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Multiple-Choice Suite | MC Avg72.1 | 49 | 29d ago | ||
| PubMedQA (test) | AUROC81.8 | 9 | 16d ago | ||
| Kazakh socio-cultural MC QA (test) | qwen-1.5b | Accuracy37.1 | 8 | 25d ago | |
| CLOTH | Accuracy84.8 | 8 | 1mo ago | ||
| RQA-MC | Decoding_r | Accuracy81 | 6 | 17d ago |