Calibration
CursorBench 4.0 → FrontierSWE v2
FrontierSWE v2 is estimated from CursorBench 4.0 with a Hill curve fitted on 8 models measured on both: y = 0.0000 + (0.8214 − 0.0000)·x^6.00 / (0.46480^6.00 + x^6.00), R² = 0.87, cross-validated error 7.6 pp. It is used for 5 estimates.
| Estimated model | CursorBench 4.0 | FrontierSWE v2 | Source |
|---|---|---|---|
| Claude Sonnet 5 | 34.1% | 11.1% | estimated ± 7.6 pp, low confidence |
| Composer 2.5 | 27.7% | 3.5% | estimated ± 7.6 pp, low confidence |
| GPT-5.6 Luna | 35.9% | 14.4% | estimated ± 7.6 pp, low confidence |
| GPT-5.6 Terra | 41.3% | 27.1% | estimated ± 7.6 pp, medium confidence |
| Muse Spark 1.3 | 41.6% | 27.9% | estimated ± 7.6 pp, medium confidence |