Medical Evaluation on MediEval
Evaluation results
| Method | Links | | | | | | | | | | |
|---|
| GPT-4oModel=GPT-4o, Adaptation=Base generative form2025.12 | | 49.3 | 31.6 | 50 | 29.1 | 66.3 | 50 | 0 | 0 | 46.7 | — |
|---|
| GPT-5Model=GPT-5, Adaptation=Base generative form2025.12 | | 45.7 | 36.4 | 46.7 | 30.4 | 68.3 | 53.3 | 0 | 0 | 19.3 | — |
|---|