benchgap
Calibration

Harvey LAB → EnterpriseOps-Gym

EnterpriseOps-Gym is estimated from Harvey LAB with a Hill curve fitted on 6 models measured on both: y = 0.0184 + (1.2000 − 0.0184)·x^6.00 / (1.01659^6.00 + x^6.00), R² = 0.85, cross-validated error 4.4 pp. It is used for 3 estimates.

Estimated modelHarvey LABEnterpriseOps-GymSource
Claude Fable 5.1 (xhigh with fallback)93.3%46.0%estimated ± 4.4 pp, medium confidence
Claude Fable 5.1 (high with fallback)93.0%45.5%estimated ± 4.4 pp, medium confidence
Muse Spark 1.3 (xhigh)95.5%50.0%estimated ± 4.4 pp, low confidence