Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
45.34Pass@16
5
Jun 4, 2026
26Score (%)
5
Jun 1, 2026
64.5Score (%)
5
Jun 1, 2026
51.2Score (%)
5
Jun 1, 2026
57.3Score (%)
5
Jun 1, 2026
65.85HE Score
5
May 29, 2026
1.94Pass@1 (Introductory)
5
May 28, 2026
2.67Pass@1
5
May 28, 2026
12.14Pass@1
5
May 28, 2026
61.1Pass@1
5
May 28, 2026
69.5HumanEval
5
May 26, 2026
4.5ECE
5
May 25, 2026
7.5ECE
5
May 25, 2026
6.3ECE
5
May 25, 2026
10.9ECE
5
May 25, 2026
3.3ECE
5
May 25, 2026
7.6ECE
5
May 25, 2026
6.4ECE
5
May 25, 2026
11.1ECE
5
May 25, 2026
57.4Accuracy
5
May 22, 2026
60.4Accuracy
5
May 22, 2026
81.71Accuracy (Acc)
5
Jun 30, 2026
42.9Pass Rate
5
May 18, 2026
64Pass Rate
5
May 18, 2026
37.53pass@8
5
May 15, 2026