Calibration
AA-GPQA Diamond → GPQA
GPQA is estimated from AA-GPQA Diamond with a linear curve fitted on 60 models measured on both: y = 0.8788·x + 0.1137, R² = 0.89, cross-validated error 5.4 pp. It is used for 0 estimates.
GPQA is estimated from AA-GPQA Diamond with a linear curve fitted on 60 models measured on both: y = 0.8788·x + 0.1137, R² = 0.89, cross-validated error 5.4 pp. It is used for 0 estimates.