Functional Correctness
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.57Pass@1
27
Jun 5, 2026
4.2U Success Rate
20
Jun 2, 2026
56.3U Score
20
Jun 2, 2026
43.9Success Rate U
20
Jun 2, 2026
38.1Functional Success Rate @1
16
Feb 26, 2026
55.2Functional Accuracy @1
16
Feb 26, 2026