Calibration

Toolathlon → GDPval-AA

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

GDPval-AA is estimated from Toolathlon with a Michaelis–Menten + offset curve fitted on 19 models measured on both: y = 0.0000 + 2.0000·x / (2.17337 + x), R² = 0.44, cross-validated error 9.6 pp. It is used for 0 estimates.