Calibration

AA Tau3 Banking → AA EnterpriseOps-Gym

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

AA EnterpriseOps-Gym is estimated from AA Tau3 Banking with a Michaelis–Menten curve fitted on 9 models measured on both: y = 0.4950·x / (0.09320 + x), R² = 0.53, cross-validated error 5.3 pp. It is used for 1 estimate.

Estimated model	AA Tau3 Banking	AA EnterpriseOps-Gym	Source
Ling 3.0 Flash	28.0%	37.1%	estimated ± 5.3 pp, medium confidence