Calibration

APEX-Agents-AA → Gert Labs

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

Gert Labs is estimated from APEX-Agents-AA with a linear curve fitted on 13 models measured on both: y = 0.6247·x + 0.3892, R² = 0.46, cross-validated error 11.3 pp. It is used for 1 estimate.

Estimated model	APEX-Agents-AA	Gert Labs	Source
Claude Opus 4.6 (Adaptive)	33.0%	59.5%	estimated ± 11.3 pp, low confidence