Calibration
Gert Labs → APEX-Agents-AA
APEX-Agents-AA is estimated from Gert Labs with a linear curve fitted on 13 models measured on both: y = 0.7370·x + -0.1773, R² = 0.46, cross-validated error 11.4 pp. It is used for 3 estimates.
| Estimated model | Gert Labs | APEX-Agents-AA | Source |
|---|---|---|---|
| Gemini 3.1 Flash-Lite | 38.5% | 10.6% | estimated ± 11.4 pp, low confidence |
| Grok 4.20 | 38.4% | 10.5% | estimated ± 11.4 pp, low confidence |
| Grok Build 0.1 | 49.2% | 18.5% | estimated ± 11.4 pp, low confidence |