Code Generation
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
76.5Average Score
47
Jun 11, 2026
61.5Accuracy
45
May 19, 2026
91.7Score
45
Jul 2, 2026
1.94Average Tau (τ)
45
Feb 26, 2026
71.95Pass@1
45
Feb 26, 2026
6.06Success Rate (SR)
43
Jun 11, 2026
70.53Pass Rate
43
Jun 23, 2026
94.2Score
43
Feb 26, 2026
90.08Accuracy
42
May 29, 2026
53.6Pass@1 Overall
42
May 12, 2026
7.07Average Acceptance Length
41
Jul 7, 2026
59.7pass@1
41
Feb 26, 2026
222.68TPS
41
Feb 26, 2026
5.67Average Speed-up
41
Feb 26, 2026
140Pass Count
40
Jun 2, 2026
56.1Pass@1
40
May 26, 2026
46.8Accuracy
40
Apr 30, 2026
61.5Pass@1
39
Jun 9, 2026
98.44Accuracy
39
Apr 28, 2026
89.02Accuracy
39
Mar 16, 2026
98.44Pass@1
39
May 15, 2026
75.1Accuracy (%)
38
Jun 30, 2026
58Score
38
Feb 27, 2026
36.5pass@1
38
Feb 26, 2026
91.7Pass@1
37
Jun 17, 2026