Calibration

AA AutomationBench → BrowseComp

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

BrowseComp is estimated from AA AutomationBench with a Michaelis–Menten curve fitted on 6 models measured on both: y = 0.9434·x / (0.02241 + x), R² = 0.85, cross-validated error 13.1 pp. It is used for 0 estimates.