Calibration
AA-HLE → GPQA
GPQA is estimated from AA-HLE with a Michaelis–Menten curve fitted on 61 models measured on both: y = 0.9722·x / (0.02821 + x), R² = 0.81, cross-validated error 6.1 pp. It is used for 0 estimates.
GPQA is estimated from AA-HLE with a Michaelis–Menten curve fitted on 61 models measured on both: y = 0.9722·x / (0.02821 + x), R² = 0.81, cross-validated error 6.1 pp. It is used for 0 estimates.