Calibration
ARC-AGI-3 → HealthBench Professional
HealthBench Professional is estimated from ARC-AGI-3 with a linear curve fitted on 9 models measured on both: y = 0.1328·x + 0.5679, R² = 0.43, cross-validated error 4.3 pp. It is used for 1 estimate.
| Estimated model | ARC-AGI-3 | HealthBench Professional | Source |
|---|---|---|---|
| Claude Opus 4.7 (Adaptive) | 0.2% | 56.8% | estimated ± 4.3 pp, medium confidence |