Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.06Speedup
12
Feb 26, 2026
49.08Pass Rate
12
Feb 26, 2026
62.56Pass Rate
12
Feb 26, 2026
70.13Pass Rate
12
Feb 26, 2026
70.86Pass Rate
12
Feb 26, 2026
5.51Speedup
12
Feb 26, 2026
4.78Speedup
12
Feb 26, 2026
96.5Pass@1 Accuracy (Python)
12
Feb 26, 2026
83.9HumanEval
12
Feb 26, 2026
87.7Pass@1 Acc
12
Feb 26, 2026
38.66pass@1
12
Feb 26, 2026
59.24Pass@1
12
Feb 26, 2026
65.76Pass@1
12
Feb 26, 2026
28.85Accuracy
11
Jul 8, 2026
72.47Accuracy
11
Jul 7, 2026
53.66Pass@1
11
Jun 9, 2026
34.76Score
11
Jul 7, 2026
30.1Pass@1
11
May 6, 2026
92.11Pass@1
11
Apr 23, 2026
28.4Score
11
Mar 13, 2026
50.4Score
11
Mar 13, 2026
50.4Pass Rate
11
Feb 26, 2026
49.99Pass Rate
11
Feb 26, 2026
100Pass@1
11
May 7, 2026
74.6Pass@1
11
Feb 26, 2026