Calibration
JobBench → Gert Labs
Gert Labs is estimated from JobBench with a Hill curve fitted on 14 models measured on both: y = 0.5020 + (1.2000 − 0.5020)·x^6.00 / (0.48760^6.00 + x^6.00), R² = 0.50, cross-validated error 7.3 pp. It is used for 4 estimates.
| Estimated model | JobBench | Gert Labs | Source |
|---|---|---|---|
| Claude 4.1 Opus | 21.9% | 50.8% | estimated ± 7.3 pp, medium confidence |
| Claude Haiku 4.5 | 16.0% | 50.3% | estimated ± 7.3 pp, medium confidence |
| GPT-5 (high) | 8.5% | 50.2% | estimated ± 7.3 pp, low confidence |
| Qwen3.5 Plus | 18.5% | 50.4% | estimated ± 7.3 pp, medium confidence |