Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.23Accuracy (%)
12
May 26, 2026
75.76Accuracy
12
May 26, 2026
42.7Pass Rate
12
May 26, 2026
69.5HE Score
12
May 15, 2026
20Accuracy
12
May 12, 2026
66Accuracy
12
May 12, 2026
42.6Accuracy
12
Apr 21, 2026
95Win-rate
12
Apr 16, 2026
97Win Rate
12
Apr 16, 2026
90Win-rate
12
Apr 16, 2026
94Win-rate
12
Apr 16, 2026
25.44Pass@1
12
Apr 7, 2026
70Accuracy@4
12
Mar 30, 2026
0.468Accuracy
12
Mar 26, 2026
58.54Accuracy
12
Mar 20, 2026
51.4Accuracy
12
Mar 20, 2026
70.72Average Score
12
Mar 17, 2026
52.46avg@32
12
Mar 17, 2026
74.5Average Success Rate (@32)
12
Mar 17, 2026
85.21Average Pass Rate @32
12
Mar 17, 2026
30.6pass@1
12
Mar 17, 2026
82.29Avg@8
12
Feb 26, 2026
27.78Avg@8
12
Feb 26, 2026
53.05Pass@1
12
Apr 3, 2026
0.68MA
12
Feb 26, 2026