Calibration

ARC-AGI-1 → AA-HLE

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

AA-HLE is estimated from ARC-AGI-1 with a offset logistic curve fitted on 32 models measured on both: y = 0.2947 + (1.0392 − 0.2947) / (1 + exp(−14.29·(x − 1.0295))), R² = 0.69, cross-validated error 6.2 pp. It is used for 1 estimate.

Estimated model	ARC-AGI-1	AA-HLE	Source
Claude Sonnet 4.5 Thinking	63.7%	29.7%	estimated ± 6.2 pp, medium confidence