| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Medical Knowledge Question Answering | Medical Domain (MedQA, MMLU, MedMCQA) (test) | MedQA Score92.5 | 45 | |
| Spearman rank correlation with retrieval | Medical Domain ROCO, MIMIC-CXR | Spearman Rho0.969 | 9 | |
| Entity Recognition | Medical Domain 8 held-out sets | EER5.84 | 8 | |
| Summarization | Medical domain (100 random samples) | Coherence3.3 | 4 | |
| Medical Reasoning | Medical domain (val) | Correctness3.8 | 2 |