Calibration

AA ITBench → AA-AnalystAgent

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

AA-AnalystAgent is estimated from AA ITBench with a linear curve fitted on 7 models measured on both: y = -0.7584·x + 0.8505, R² = 0.30, cross-validated error 8.5 pp. It is used for 1 estimate.

Estimated model	AA ITBench	AA-AnalystAgent	Source
GLM-5.2	42.7%	52.7%	estimated ± 8.5 pp, low confidence