Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67.1BLEU
10
Feb 26, 2026
8.58NFE Reduction
9
Jun 12, 2026
6.96NFE Reduction
9
Jun 12, 2026
47Pass@1
9
Jun 9, 2026
57.3Pass@1
9
Jun 9, 2026
35.4Accuracy
9
Jun 2, 2026
0.738Accuracy
9
Jun 2, 2026
73.8HEVAL+ Score
9
May 29, 2026
13.8Accuracy
9
Jun 8, 2026
0.429nR2
9
May 20, 2026
82.93Accuracy
9
May 15, 2026
98.2Accuracy
9
May 15, 2026
90TSR
9
May 13, 2026
81.6IFS
9
May 12, 2026
5.71Inference SpeedUp
9
May 12, 2026
59.15Pass@2
9
Apr 23, 2026
57.6Accuracy
9
Apr 21, 2026
33.2Score
9
May 22, 2026
75Pass@3
9
Apr 16, 2026
39.3Pass@3
9
Apr 16, 2026
77Pass@3
9
Apr 16, 2026
59Pass@3
9
Apr 16, 2026
94Pass@3
9
Apr 16, 2026
89Accuracy
9
Apr 16, 2026
34.2Accuracy
9
Apr 13, 2026