benchgap
Calibration

HealthBench (length-adjusted) → ARC-AGI-3

ARC-AGI-3 is estimated from HealthBench (length-adjusted) with a linear curve fitted on 5 models measured on both: y = 10.4190·x + -5.5819, R² = 0.84, cross-validated error 14.4 pp. It is used for 0 estimates.

Fitted on

ModelHealthBench (length-adjusted)ARC-AGI-3
Claude Opus 557.8%30.2%
GPT-6.1 Sol58.5%52.7%
GPT-6 Astra58.3%62.7%
GPT-6 Luna54.5%0.1%
GPT-6 Sol53.2%4.6%