Calibration

AA EnterpriseOps-Gym → GDPval-AA

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

GDPval-AA is estimated from AA EnterpriseOps-Gym with a inverse Michaelis–Menten curve fitted on 12 models measured on both: y = 1.63322·(x − 0.0000) / (0.0000 + 2.0000 − x), R² = 0.40, cross-validated error 10.9 pp. It is used for 0 estimates.