Calibration
OpenHarmony Bench → Vals SWE-bench
Vals SWE-bench is estimated from OpenHarmony Bench with a linear curve fitted on 11 models measured on both: y = 1.6632·x + -0.0797, R² = 0.52, cross-validated error 7.3 pp. It is used for 0 estimates.
Vals SWE-bench is estimated from OpenHarmony Bench with a linear curve fitted on 11 models measured on both: y = 1.6632·x + -0.0797, R² = 0.52, cross-validated error 7.3 pp. It is used for 0 estimates.