Calibration

FrontierSWE v2 → AA Coding Index

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

AA Coding Index is estimated from FrontierSWE v2 with a Hill curve fitted on 12 models measured on both: y = 0.0000 + (0.7857 − 0.0000)·x^1.63 / (0.02705^1.63 + x^1.63), R² = 0.96, cross-validated error 2.7 pp. It is used for 0 estimates.