benchgap
Calibration

MMMU-Pro w/ Python → MMMU-Pro

MMMU-Pro is estimated from MMMU-Pro w/ Python with a Hill curve fitted on 9 models measured on both: y = 0.2496 + (0.9546 − 0.2496)·x^6.00 / (0.65709^6.00 + x^6.00), R² = 1.00, cross-validated error 0.6 pp. It is used for 0 estimates.