Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
3.81SR
16
May 20, 2026
38.3Average Score (@16)
16
May 18, 2026
44.8Average@8
16
May 18, 2026
1.3Average Rank
16
May 11, 2026
15.2Pass@1
16
Apr 3, 2026
92.37Score (%)
16
Feb 26, 2026
87.53Execution Score
16
Feb 26, 2026
68.9Pass@1
16
May 1, 2026
91.5HumanEval
16
Feb 27, 2026
65.1MBPP Pass@1
16
Feb 26, 2026
85.63Accuracy
16
Jun 2, 2026
35.45Pass@1
16
Feb 26, 2026
97.86Pass Rate
15
Jun 23, 2026
99.78Pass%
15
Jun 23, 2026
87.4Accuracy
15
Jun 16, 2026
35.85Pass@1 (LCB-v5)
15
Jun 1, 2026
97.8Trigger Rate
15
May 28, 2026
90.9HEval
15
May 26, 2026
98.2Accuracy (HumanEval)
15
May 15, 2026
39.1LCBv6 Score
15
May 13, 2026
7.54MAT Score
15
Apr 24, 2026
55.8Success Rate (SR)
15
Apr 1, 2026
79.3Accuracy
15
Mar 27, 2026
68.6Matplotlib Score
15
Mar 24, 2026
2,439Pass@1
15
Mar 24, 2026