Calibration
AA-GPQA Diamond → HealthBench Professional
HealthBench Professional is estimated from AA-GPQA Diamond with a offset logistic curve fitted on 7 models measured on both: y = 0.5509 + (0.6420 − 0.5509) / (1 + exp(−200.00·(x − 0.9357))), R² = 0.50, cross-validated error 4.9 pp. It is used for 2 estimates.
| Estimated model | AA-GPQA Diamond | HealthBench Professional | Source |
|---|---|---|---|
| o1-preview | 76.5% | 55.1% | estimated ± 4.9 pp, low confidence |
| o3-pro | 84.5% | 55.1% | estimated ± 4.9 pp, low confidence |