benchgap
Calibration

AA-GPQA Diamond → GPQA Diamond

GPQA Diamond is estimated from AA-GPQA Diamond with a Hill curve fitted on 40 models measured on both: y = 0.6452 + (1.2000 − 0.6452)·x^6.00 / (0.92621^6.00 + x^6.00), R² = 0.84, cross-validated error 4.3 pp. It is used for 0 estimates.