Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
42.9Avg@8
22
Feb 26, 2026
85.2MBPP Accuracy
22
Feb 26, 2026
29.1Pass@1
22
Apr 28, 2026
75.6pass@1
21
Jun 18, 2026
81.1pass@1
21
Jun 18, 2026
24.75Pass@1
21
May 29, 2026
38Signal
21
May 25, 2026
46.7Signal Score
21
May 25, 2026
58.7Signal
21
May 25, 2026
86pass@1
21
May 19, 2026
86.6Accuracy (%)
21
May 19, 2026
55.2Pass@1
21
May 25, 2026
77Accuracy (Pass@4)
21
May 12, 2026
55.6Flex (%)
21
May 12, 2026
55.5Flexibility
21
May 12, 2026
75.9Accuracy
21
Jun 17, 2026
73.1FUNC Score
21
Apr 7, 2026
20.46CF Score
21
Mar 19, 2026
20.79LCB Score
21
Mar 19, 2026
37.63Score
21
Jun 30, 2026
87.24Overall Accuracy
21
Mar 24, 2026
68.29Pass@1
21
Jun 17, 2026
77.1Accuracy
21
Feb 26, 2026
73.8PR
21
Feb 27, 2026
64.62PR
21
Feb 27, 2026