Calibration
APEX-Agents-AA → GDPval-AA
GDPval-AA is estimated from APEX-Agents-AA with a linear curve fitted on 26 models measured on both: y = 0.9419·x + 0.0766, R² = 0.61, cross-validated error 11.2 pp. It is used for 1 estimate.
| Estimated model | APEX-Agents-AA | GDPval-AA | Source |
|---|---|---|---|
| Claude Opus 4.6 (Adaptive) | 33.0% | 38.7% | estimated ± 11.2 pp, low confidence |