Calibration
DAYJOB Healthcare → DAYJOB
DAYJOB is estimated from DAYJOB Healthcare with a Michaelis–Menten curve fitted on 19 models measured on both: y = 0.4763·x / (0.22251 + x), R² = 0.98, cross-validated error 1.5 pp. It is used for 0 estimates.
Fitted on
| Model | DAYJOB Healthcare | DAYJOB |
|---|---|---|
| Claude Opus 4.8 | 0.8% | 2.0% |
| Claude Opus 5 | 9.2% | 11.7% |
| Claude Opus 5.5 | 25.2% | 24.5% |
| Claude Sonnet 5 | 0.0% | 1.7% |
| Claude Sonnet 5.5 | 16.0% | 21.7% |
| Gemini 3.1 Pro | 0.0% | 0.0% |
| Gemini 3.5 Flash-Lite | 0.0% | 0.0% |
| Gemini 3.8 Flash | 1.2% | 2.6% |
| Gemini 3 Flash | 0.0% | 0.0% |
| Gemini 4 Argon | 11.6% | 15.7% |
| Gemini 4 Carbon | 15.6% | 19.7% |
| GPT-5.5 | 0.0% | 1.4% |
| GPT-5.6 Luna | 1.2% | 1.1% |
| GPT-5.6 Sol | 1.2% | 4.2% |
| GPT-5.6 Terra | 2.0% | 2.8% |
| GPT-6.1 Sol | 10.8% | 15.5% |
| GPT-6 Astra | 11.2% | 17.4% |
| GPT-6 Luna | 1.2% | 1.2% |
| GPT-6 Sol | 2.8% | 6.8% |