Calibration
Toolathlon → Gert Labs
Gert Labs is estimated from Toolathlon with a Hill curve fitted on 13 models measured on both: y = 0.4542 + (1.2000 − 0.4542)·x^6.00 / (0.65907^6.00 + x^6.00), R² = 0.67, cross-validated error 7.2 pp. It is used for 3 estimates.
| Estimated model | Toolathlon | Gert Labs | Source |
|---|---|---|---|
| GLM-5.2 | 48.2% | 55.3% | estimated ± 7.2 pp, medium confidence |
| GPT-5.4 mini | 42.9% | 50.7% | estimated ± 7.2 pp, medium confidence |
| GPT-5.4 nano | 35.5% | 47.2% | estimated ± 7.2 pp, medium confidence |