Calibration
CritPt → Vals MMLU-Pro
Vals MMLU-Pro is estimated from CritPt with a linear curve fitted on 47 models measured on both: y = 0.2136·x + 0.8411, R² = 0.34, cross-validated error 2.7 pp. It is used for 0 estimates.
Vals MMLU-Pro is estimated from CritPt with a linear curve fitted on 47 models measured on both: y = 0.2136·x + 0.8411, R² = 0.34, cross-validated error 2.7 pp. It is used for 0 estimates.