Calibration
CursorBench 3.2 → Vals SWE-bench
Vals SWE-bench is estimated from CursorBench 3.2 with a Michaelis–Menten curve fitted on 17 models measured on both: y = 1.7794·x / (0.63684 + x), R² = 0.52, cross-validated error 5.5 pp. It is used for 0 estimates.