Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
48.02Pass Rate
6
Feb 26, 2026
38.6Pass Rate
6
Feb 26, 2026
72.44Pass Rate
6
Feb 26, 2026
77.19Pass Rate
6
Feb 26, 2026
41Pass@1
6
Feb 26, 2026
59.5Last Epoch Success Rate
6
Feb 26, 2026
50.8Success Rate
6
Feb 26, 2026
0.459Accuracy
6
Feb 26, 2026
64.6pass@5
6
Feb 26, 2026
89Score
6
Feb 26, 2026
0.37Cost
6
Feb 26, 2026
0.46Cost
6
Feb 26, 2026
35.2Pass@5
6
Feb 26, 2026
46.5English Overall Pass@1
6
Feb 26, 2026
35.1ROUGE-1 F1
6
Feb 26, 2026
16.66BLEU
6
Feb 26, 2026
27.53BLEU
6
Feb 26, 2026
63.5Train Success Rate
5
Jul 7, 2026
62.65Accuracy
5
Jul 7, 2026
60.37Accuracy
5
Jul 7, 2026
92.88LCB Accuracy (Easy)
5
Jun 30, 2026
22.2Achieved
5
Jun 23, 2026
25.9End pass@1
5
Jun 23, 2026
45.38Accuracy
5
Jun 17, 2026
87.7MTP Acceptance Rate
5
Jun 11, 2026