Code Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
74.2Accuracy (KodCode Test)
13
May 22, 2026
1,533.64Rating
12
May 4, 2026
51Score
12
Feb 26, 2026
88.3Pass@1 Accuracy
11
Apr 10, 2026
74Accuracy
9
Jun 1, 2026
92Pass@1
8
Jun 8, 2026
41Pass@1
8
May 22, 2026
7.7Pass@1
8
May 22, 2026
15.3Accuracy
8
Mar 4, 2026
28.71Pass@1
7
Jun 12, 2026
25.75CRUX Score
6
Jul 7, 2026
73.8Accuracy avg@32
6
May 8, 2026
75.4Avg@8 Score
6
Apr 21, 2026
40.75Accuracy
6
Feb 26, 2026
37.6Pass@1
5
May 21, 2026
36.8Pass@1
5
Mar 20, 2026
89.3Pass@1
5
Mar 20, 2026
88.4Pass@1
5
Mar 20, 2026
55.83Accuracy
5
Feb 26, 2026
0.677Accuracy
5
Feb 26, 2026
85.36Accuracy
4
May 22, 2026
42.1Pass@1
4
Mar 20, 2026
28.7Pass@1
3
May 12, 2026
40BigCodeBench Score
3
Feb 26, 2026
63.3Avg@10
2
May 13, 2026