Coding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
92.5Pass@1
27
Jun 16, 2026
86.7Eval+ Score
26
Mar 9, 2026
0.26KL Divergence (Forward)
24
May 11, 2026
79Task Accuracy
23
Feb 26, 2026
94.16Score
23
May 22, 2026
94.57Precision
21
Feb 26, 2026
84.8Accuracy
20
May 28, 2026
67.7Pass@1
19
Jun 9, 2026
96.3Score
19
Jun 18, 2026
94.5Accuracy
19
Apr 21, 2026
93.9Accuracy
19
Apr 21, 2026
87.5Score
19
May 26, 2026
69.11Pass@1
19
Mar 4, 2026
3,070Throughput
18
Mar 20, 2026
3,413Throughput
18
Mar 20, 2026
80.2Accuracy
16
Jun 16, 2026
100Pass@16
16
Mar 6, 2026
90.7Accuracy
16
Feb 26, 2026
94.1Pass@10
16
Feb 26, 2026
69.9Aggregate Average Score
15
May 19, 2026
33.8Pass@1
15
May 19, 2026
54pass@1
15
May 19, 2026
92Pass@1
15
May 19, 2026
91.5Pass@1
15
May 19, 2026
78.86Pass@1
15
Mar 24, 2026