benchgap
Calibration

MedXpertQA (MM) → CharXiv

CharXiv is estimated from MedXpertQA (MM) with a Michaelis–Menten curve fitted on 6 models measured on both: y = 2.0000·x / (1.09365 + x), R² = 0.41, cross-validated error 11.8 pp. It is used for 0 estimates.