Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77.43Accuracy
18
Mar 9, 2026
2.3Speed
18
Feb 26, 2026
2.4Speed (Spd)
18
Feb 26, 2026
41.44pass@1
18
Feb 26, 2026
73.33Pass@1
18
Feb 26, 2026
90.9Pass@1
18
Mar 5, 2026
0.992Pass@1
18
Feb 26, 2026
30.7pass@1
18
Feb 26, 2026
48.2HumanEval
18
Feb 26, 2026
32.93Tokens/s
18
Feb 26, 2026
19.18Accuracy
18
Feb 26, 2026
56.57Accuracy
18
Feb 26, 2026
64.07Accuracy
18
Feb 26, 2026
94.94Accuracy
18
Apr 14, 2026
21.38PR
18
Feb 27, 2026
79.5Pass@1
18
Feb 26, 2026
64.6Pass@1
18
Feb 26, 2026
28.74Accuracy
17
Jul 8, 2026
87.3Pass@1
17
Jul 8, 2026
87.2Pass@1
17
Jul 8, 2026
63.1Pass@1
17
Jul 3, 2026
78.9Pass@1
17
Jul 3, 2026
65MB Score
17
Jun 11, 2026
48.7HumanEval Score
17
Jun 11, 2026
26.9Accuracy
17
Jun 9, 2026