Coding Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
63.1Success Rate
36
Jun 2, 2026
50Success Rate
36
Jun 2, 2026
58.46Pass@1
24
May 12, 2026
58.55Success Rate
18
Jun 2, 2026
39.28Success Rate
18
Jun 2, 2026
80Knowledge Recall
16
May 26, 2026
96.34Accuracy (%)
16
Jun 16, 2026
58.1Pass@1 (avg@8)
11
Apr 2, 2026
0.705Accuracy
11
Feb 26, 2026
93.28Avg@4
8
Jun 16, 2026
73.5Medium Pass@1
6
May 14, 2026
82.8Pass@4
6
May 12, 2026
70.8Accuracy
6
Apr 3, 2026
48.4Pass Rate
5
Feb 27, 2026
71.2Pass Rate
5
Feb 27, 2026
65.8Pass Rate
5
Feb 27, 2026
68.3Pass Rate
5
Feb 27, 2026
66.11Accuracy (%)
4
May 20, 2026
53.4Avg@4
3
Feb 26, 2026