Calibration

AA EnterpriseOps-Gym → AA Tau3 Banking

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

AA Tau3 Banking is estimated from AA EnterpriseOps-Gym with a Hill curve fitted on 9 models measured on both: y = 0.0000 + (0.5459 − 0.0000)·x^6.00 / (0.32563^6.00 + x^6.00), R² = 0.55, cross-validated error 12.1 pp. It is used for 0 estimates.