Coding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
74.6Accuracy
5
May 15, 2026
89.4Accuracy
5
May 15, 2026
99.1Accuracy
5
May 15, 2026
84.3Accuracy
5
May 15, 2026
38.9Accuracy (Acc)
5
Apr 28, 2026
47.7Initial F1
5
Apr 28, 2026
47.4Initial F1 Score
5
Apr 28, 2026
56.7Pass@1
5
Mar 31, 2026
55.64Score
5
Feb 26, 2026
35.7Score
5
Feb 26, 2026
35Accuracy
4
Jun 9, 2026
4.36Acceptance Length
4
May 12, 2026
2.26Avg Accepted Draft Tokens/Round
4
May 12, 2026
65.9Pass@1
4
Apr 30, 2026
93Pass@3
4
Apr 16, 2026
75Accuracy
4
Apr 8, 2026
3.62Turns
4
Feb 26, 2026
76.12CRUXEval-O Score
4
Feb 26, 2026
79.74Mean@4
4
Feb 26, 2026
3.5Score
4
Feb 26, 2026
89.9Score
4
Feb 26, 2026
19.5Pass@1
4
Feb 26, 2026
119Pass Count
3
Jun 26, 2026
83.72Coding Accuracy
3
Jun 19, 2026
63.8Pass Rate
3
May 14, 2026