Calibration
Vibe Code Bench → FrontierCode 1.1 Main
FrontierCode 1.1 Main is estimated from Vibe Code Bench with a inverse Michaelis–Menten curve fitted on 5 models measured on both: y = 0.74004·(x − 0.0000) / (0.0000 + 2.0000 − x), R² = 0.85, cross-validated error 4.3 pp. It is used for 2 estimates.
| Estimated model | Vibe Code Bench | FrontierCode 1.1 Main | Source |
|---|---|---|---|
| Claude Opus 4.6 (Adaptive) | 53.5% | 27.0% | estimated ± 4.3 pp, medium confidence |
| GPT-5.2-Codex | 37.9% | 17.3% | estimated ± 4.3 pp, low confidence |
Fitted on
| Model | Vibe Code Bench | FrontierCode 1.1 Main |
|---|---|---|
| Claude Opus 4.6 | 57.6% | 26.9% |
| Claude Opus 4.7 | 71.0% | 38.5% |
| Claude Sonnet 4.6 | 51.5% | 24.3% |
| GPT-5.4 mini | 48.0% | 27.0% |
| GPT-5.5 | 69.8% | 43.0% |