Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
54Pass Rate
3
Jun 30, 2026
39.4Accuracy
3
Jun 16, 2026
23.6Accuracy
3
Jun 15, 2026
46.18Pass@1
3
Jun 9, 2026
93.29Pass@1
3
Jun 9, 2026
54Pass Rate
3
Jun 9, 2026
0.555Score
3
May 27, 2026
81.09Score
3
May 27, 2026
78.51Score
3
May 27, 2026
8.47Score
3
May 27, 2026
55.5HumanEval Score
3
May 27, 2026
24.57Score
3
May 22, 2026
38.24Mean F1 Score
3
May 21, 2026
37.2Accuracy
3
May 19, 2026
42.68Accuracy
3
May 19, 2026
80.5Accuracy
3
May 7, 2026
23.6Pass@1
3
Apr 28, 2026
24.5Pass@1
3
Apr 28, 2026
27.4Pass@1
3
Apr 28, 2026
9.54TPS (Tokens/s)
3
Apr 21, 2026
67.69TPS
3
Apr 21, 2026
50.4Pass Rate Before
3
Apr 20, 2026
35.98Pass Rate Before
3
Apr 20, 2026
36.8LCB Avg@16
3
Apr 20, 2026
35.4Pass@1
3
Apr 14, 2026