Calibration
AA-GPQA Diamond → Vals MMLU-Pro
Vals MMLU-Pro is estimated from AA-GPQA Diamond with a linear curve fitted on 47 models measured on both: y = 0.3814·x + 0.5282, R² = 0.41, cross-validated error 3.0 pp. It is used for 0 estimates.
Vals MMLU-Pro is estimated from AA-GPQA Diamond with a linear curve fitted on 47 models measured on both: y = 0.3814·x + 0.5282, R² = 0.41, cross-validated error 3.0 pp. It is used for 0 estimates.