Calibration

MMLU-Pro → AA-HLE

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

AA-HLE is estimated from MMLU-Pro with a Hill curve fitted on 36 models measured on both: y = 0.0000 + (1.2000 − 0.0000)·x^6.00 / (1.08310^6.00 + x^6.00), R² = 0.59, cross-validated error 7.3 pp. It is used for 0 estimates.