benchgap
Calibration

HealthBench Professional (raw) → HealthBench (raw)

HealthBench (raw) is estimated from HealthBench Professional (raw) with a linear curve fitted on 7 models measured on both: y = 1.2519·x + -0.2718, R² = 0.98, cross-validated error 1.5 pp. It is used for 0 estimates.