Code Editing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
3.04Debug Success Rate
33
Jun 5, 2026
60Pass@1
17
Feb 26, 2026
1.5Average Tries
17
Feb 26, 2026
66.67Pass@1
13
Mar 17, 2026
39.9Pass@1 (Average)
9
Feb 26, 2026
61.7Accuracy
6
Feb 26, 2026