Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80.96Accuracy
94
Jun 9, 2026
83.6Accuracy
93
Jun 23, 2026
54.2Pass@1
91
Jun 18, 2026
100Accuracy
91
Jun 17, 2026
91.8Pass@1
91
Mar 4, 2026
96.6Accuracy
90
Feb 26, 2026
90.5Accuracy
89
May 20, 2026
90.7Pass@1
89
Feb 26, 2026
7.68Speedup
87
Jun 26, 2026
95.8Pass@1
86
Feb 27, 2026
88.6Accuracy
84
May 29, 2026
85.2Accuracy
82
May 12, 2026
91.56Score
78
Jun 17, 2026
85.6Overall Average Score
78
Jun 19, 2026
63.8Accuracy (%)
77
Feb 26, 2026
88.1Pass@1
76
May 12, 2026
95.1Pass Rate
75
May 19, 2026
83.84Accuracy
75
Jun 4, 2026
7.81Speedup
75
Jul 7, 2026
35.1Pass@1
73
Jun 18, 2026
168Average Score
68
Feb 27, 2026
89.09Pass@1
68
May 18, 2026
1,200Pass@1
68
May 27, 2026
98.27Acc
65
Mar 4, 2026
73.2Accuracy
64
May 8, 2026