Code
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.34HumanEval Accuracy
118
Jun 2, 2026
91.05Pass@1
73
Jun 2, 2026
79.9Accuracy
43
May 26, 2026
50.8Accuracy
33
Apr 3, 2026
47.1Accuracy
33
Apr 3, 2026
83.6Accuracy
30
Apr 30, 2026
55.08Accuracy @5
27
Apr 29, 2026
97.1Concat Score
21
Apr 24, 2026
87.7Score
20
Jun 2, 2026
58.1HumanEval Success Rate
17
May 19, 2026
64.3AVG@8
16
Jul 7, 2026
67.19Average Performance
16
May 27, 2026
90.7Score
14
Jul 2, 2026
8.37Speedup
12
May 29, 2026
7.68Speedup
12
May 29, 2026
29.94Score
10
May 19, 2026
9.021Perplexity
10
Feb 26, 2026
67.3Pass@1
9
Jun 2, 2026
93.77Score
9
Jun 2, 2026
39.75Score
9
May 26, 2026
13.88Score
9
May 26, 2026
40Score
9
May 26, 2026
67.07Pass@1
9
Mar 4, 2026
1True WS Score
8
May 25, 2026
85.97pass@1
8
Jun 16, 2026