| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | MedQUAD | PRR58.3 | 66 | |
| Selective Generation | MedQUAD | ROC-AUC0.928 | 66 | |
| Selective Generation | MedQUAD | PRR (ROUGE-L)46.6 | 14 | |
| Selective Generation | MedQUAD Out-of-domain | PRR (ROUGE-L)30.4 | 8 | |
| Medical Question Answering | MedQuAD-style Complete Benchmark | MedQuAD Score91.1 | 5 | |
| Medical Question Answering | MedQuAD (test) | ROUGE-153 | 4 | |
| Medical Reasoning | MedQuAD complete benchmark | Failure Rate0 | 1 |