Calibration

AA AutomationBench → AA-AnalystAgent

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

AA-AnalystAgent is estimated from AA AutomationBench with a Hill curve fitted on 10 models measured on both: y = 0.1325 + (0.6282 − 0.1325)·x^6.00 / (0.52446^6.00 + x^6.00), R² = 0.90, cross-validated error 8.5 pp. It is used for 0 estimates.