Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
11.66EM
9
Feb 26, 2026
2.64Pass@1
9
Mar 4, 2026
61.4BLEU
9
Feb 26, 2026
2.74Speedup
8
Jun 26, 2026
79.01Accuracy (%)
8
Jun 19, 2026
43.22Avg@8
8
Jun 18, 2026
20.39Pass@10
8
Jun 16, 2026
72.5Accuracy
8
Jun 2, 2026
4.93Latency (ms/tok)
8
Jun 2, 2026
5.26Time per Token (ms/tok)
8
Jun 2, 2026
62.6Accuracy
8
May 29, 2026
0.572Mean Score
8
May 21, 2026
83Accuracy
8
May 19, 2026
90.3Pass Rate (Easy)
8
May 19, 2026
80.97Pass@1
8
May 14, 2026
99.32Release Rate
8
May 14, 2026
0False Release Rate
8
May 14, 2026
61.82Mean@8
8
May 14, 2026
63.99Accuracy
8
May 13, 2026
53.05Accuracy
8
May 13, 2026
26.3QD-Score
8
May 12, 2026
67.8Accuracy
8
May 12, 2026
80.9ACC*
8
Apr 14, 2026
81.7Pass@1
8
Apr 7, 2026
73.4PASS@1
8
Apr 7, 2026