Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.4Pass@1 (Easy)
9
Mar 31, 2026
85.45Pass@128
9
Mar 18, 2026
81.2Accuracy
9
Mar 18, 2026
72.53Accuracy
9
Feb 26, 2026
85.56Pass@1
9
Feb 26, 2026
62.6Average Accuracy
9
Feb 26, 2026
90Accuracy
9
Feb 26, 2026
284TPF
9
Feb 26, 2026
4.09TPF
9
Feb 26, 2026
56.12Avg@3 Accuracy
9
Feb 26, 2026
88.43Avg Accuracy @16
9
Feb 26, 2026
77.49MBPP avg@16 Accuracy
9
Feb 26, 2026
48.2Acc
9
Feb 26, 2026
0.406Accuracy
9
Feb 26, 2026
58.8Score
9
Jun 12, 2026
25.7DBS
9
Feb 26, 2026
38.74ATS
9
Feb 26, 2026
75.2Pass Rate
9
Feb 26, 2026
27.97PR
9
Feb 27, 2026
25Pass@1
9
Feb 26, 2026
24.1Pass@1
9
Feb 26, 2026
23.2Pass@1
9
Feb 26, 2026
27Pass@1 (Class-level)
9
Feb 26, 2026
48Pass@1 Average
9
Feb 26, 2026
1,183EM
9
Feb 26, 2026