Calibration
AA-HLE → BioMysteryBench (human-difficult)
BioMysteryBench (human-difficult) is estimated from AA-HLE with a Michaelis–Menten curve fitted on 6 models measured on both: y = 0.8738·x / (0.43202 + x), R² = 0.42, cross-validated error 8.1 pp. It is used for 0 estimates.