Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
25.64Pass@1
5
Feb 26, 2026
59.6Accuracy
5
Feb 26, 2026
5Solved Problems
5
Feb 26, 2026
17Solved Problems
5
Feb 26, 2026
220Pass@1
5
Feb 26, 2026
490Pass@1
5
Feb 26, 2026
34Pass@1
4
Jul 9, 2026
75.5S-opt
4
Jun 30, 2026
496.19Time Per Sample (TPS)
4
Jun 30, 2026
0.26Cost (cents)
4
Jun 26, 2026
93.8Quality (%)
4
Jun 26, 2026
37.7Pass@1
4
Jun 23, 2026
58.66Pass@1
4
Jun 16, 2026
30.7Pass Rate
4
Jun 9, 2026
1,666ELO
4
Jun 9, 2026
62.2Avg@8 Accuracy
4
Jun 5, 2026
51.96Tokens Per Second (TPS)
4
Jun 4, 2026
44.77TPS (Tokens/s)
4
Jun 4, 2026
28.03TPS
4
Jun 4, 2026
35.69TPS
4
Jun 4, 2026
75.4WS Prefix Match
4
Jun 2, 2026
30.8Pass@1 Accuracy (N=64)
4
Jun 2, 2026
61Accuracy
4
May 28, 2026
79.4Pass@4
4
May 27, 2026
73.8All-Passed Rate
4
May 27, 2026