| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Medical Question Answering | MedBullets | Accuracy84.2 | 65 | |
| Medical Question Answering | MedBullets (test) | Accuracy82.79 | 18 | |
| Medical Reasoning | MedBullets | Accuracy80.8 | 13 | |
| Medical Reasoning | MedBullets | Token Cost (tokens/question)2,391 | 11 | |
| Medical Question Answering | Medbullets op5 | Accuracy53.9 | 8 | |
| Medical Reasoning | Medbullets OOD (out-of-distribution) | Accuracy63.6 | 7 | |
| Medical Reasoning | MedBullets 5-option multiple choice | Accuracy53.9 | 7 | |
| Medical Reasoning | MedBullets 4-option multiple choice | Accuracy62.3 | 7 | |
| Question Answering | Medbullets 5 | Accuracy65.3 | 7 | |
| Medical Knowledge Evaluation | Medbullets | Accuracy58.44 | 5 | |
| Medical Question Answering | Medbullets op5 | Pass@194.16 | 4 | |
| Medical Question Answering | Medbullets op4 | Pass@195.78 | 4 |