OpenCompass's NEJMAI wrapper evaluates zero-shot multiple-choice answering on 858 nephSAP nephrology questions.
unassessed
| Category | domain |
|---|---|
| Subcategory | medical knowledge |
| Page status | active |
| Metric | accuracy |
| Direction | higher_is_better |
| Unit | percent |
| Dataset size | 858 |
| Publisher | Nephrology Self-Assessment Program / OpenCompass |
The OpenCompass configuration identifies a medical question, answer options, subject, and prompt mode. The linked benchmark paper evaluates 858 Nephrology Self-Assessment Program questions, not a general NEJM exam.
Medical multiple-choice question with options A through E; output one option letter.
No model card in ModelSpec reports this benchmark yet.