Calibration

MMAnswerBench → HMMT Feb 2025

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

HMMT Feb 2025 is estimated from MMAnswerBench with a Michaelis–Menten curve fitted on 7 models measured on both: y = 2.0000·x / (0.91240 + x), R² = 0.33, cross-validated error 2.4 pp. It is used for 0 estimates.