MedXpertQA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Medical Visual Question Answering | MedXpertQA | Accuracy56 | 52 | |
| Clinical Question Answering | MedXpertQA Multimodal modality (offline) | Accuracy54.73 | 38 | |
| Clinical Question Answering | MedXpertQA Text modality (offline) | Accuracy46.49 | 38 | |
| Multi-modal Question Answering | MedXpertQA-MM | Accuracy62.4 | 38 | |
| Question Answering | MedXpertQA standard (test) | Accuracy41.7 | 32 | |
| Medical Question Answering | MedXpertQA | Accuracy22.2 | 31 | |
| Medical Question Answering | MedXpertQA (test) | ETS Score8.49 | 23 | |
| Medical Reasoning | MedXpertQA | Accuracy42.9 | 20 | |
| Medical Question Answering | MedXpertQA-U | Pass@112.39 | 18 | |
| Visual Question Answering | MedXpertQA Pathology 90 samples | Accuracy25.56 | 18 | |
| Medical Visual Question Answering | MedXpertQA OOD (test) | ECE0.184 | 15 | |
| Medical Question Answering | MedXpertQA OOD (test) | Accuracy69.2 | 15 | |
| Clinical Diagnosis | MedXpertQA (OOD) | Exact Match (EM)22.97 | 14 | |
| Medical Question Answering | MedXpertQA Expert 2450 | Accuracy72 | 13 | |
| Text-only Question Answering | MedXpertQA text | Accuracy48.9 | 12 | |
| Visual Question Answering | MedXpertQA Path | Accuracy80 | 10 | |
| Clinical Diagnosis | MedXpertQA | EM7.52 | 9 | |
| Medical Question Answering | MedXpertQA Path | Accuracy60 | 9 | |
| Medical | MedXpertQA | Accuracy15.25 | 8 | |
| Question Answering | MedXpertQA (test) | Accuracy44.5 | 8 | |
| Medical Question Answering | MedXpertQA OOD Text-only | Accuracy (OOD Text-only)54.6 | 7 | |
| Medical Reasoning QA | MedXpertQA Text | Accuracy24.12 | 6 | |
| Knowledge and reasoning | MedXpertQA text + MM | Accuracy (MedXpertQA Text+MM)74.4 | 6 | |
| Text evaluation | MedXpertQA Text Only | Accuracy78.2 | 6 | |
| Medical Question Answering | MedXpertQA-Text | Pass@169.47 | 4 |
Showing 25 of 27 rows