Calibration

AutomationBench → ExploitGym

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

ExploitGym is estimated from AutomationBench with a Hill curve fitted on 7 models measured on both: y = 0.3559 + (0.0000 − 0.3559)·x^6.00 / (0.50240^6.00 + x^6.00), R² = 0.48, cross-validated error 12.5 pp. It is used for 0 estimates.