Calibration

HLE w/ tools → GDPval-AA

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

GDPval-AA is estimated from HLE w/ tools with a Hill curve fitted on 13 models measured on both: y = 0.2799 + (1.2000 − 0.2799)·x^6.00 / (0.71435^6.00 + x^6.00), R² = 0.74, cross-validated error 8.1 pp. It is used for 1 estimate.

Estimated model	HLE w/ tools	GDPval-AA	Source
Agents-A1	47.6%	35.4%	estimated ± 8.1 pp, medium confidence