Clinical Question Answering on ESAP endocrinology examination 2025 (test)
91.2Diagnosis AccuracyMirror
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Mirror2026.02 | 91.2 | 85.1 | 86.3 | 86.8 | 86.7 | 87.5 | |
| GPT-5.22026.02 | 77.6 | 70 | 70.8 | 80 | 74.7 | 74.6 | |
| GPT-52026.02 | 73.7 | 68.7 | 72.2 | 81.6 | 73.8 | 74 | |
| Gemini-3-Pro2026.02 | 71.8 | 65.5 | 64.4 | 71.1 | 76.1 | 69.8 |