benchgap
Calibration

HealthBench (raw) → HealthBench (length-adjusted)

HealthBench (length-adjusted) is estimated from HealthBench (raw) with a Michaelis–Menten curve fitted on 7 models measured on both: y = 0.9378·x / (0.35606 + x), R² = 0.73, cross-validated error 2.8 pp. It is used for 0 estimates.