Calibration
HealthBench Hard → GPQA
GPQA is estimated from HealthBench Hard with a linear curve fitted on 6 models measured on both: y = 0.1148·x + 0.8970, R² = 0.35, cross-validated error 1.7 pp. It is used for 0 estimates.
GPQA is estimated from HealthBench Hard with a linear curve fitted on 6 models measured on both: y = 0.1148·x + 0.8970, R² = 0.35, cross-validated error 1.7 pp. It is used for 0 estimates.