Calibration
MMLU-Redux → GPQA Diamond
GPQA Diamond is estimated from MMLU-Redux with a linear curve fitted on 7 models measured on both: y = 2.7820·x + -1.7132, R² = 0.93, cross-validated error 7.9 pp. It is used for 0 estimates.
GPQA Diamond is estimated from MMLU-Redux with a linear curve fitted on 7 models measured on both: y = 2.7820·x + -1.7132, R² = 0.93, cross-validated error 7.9 pp. It is used for 0 estimates.