Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
55.5Accuracy
8
Apr 6, 2026
62Pass@1
8
Apr 3, 2026
36pass@1
8
Apr 3, 2026
53.7pass@16 (MBPP)
8
Mar 26, 2026
19.7Pass@1
8
Mar 11, 2026
55.6Accuracy
8
Mar 6, 2026
56.7Pass@1
8
Mar 5, 2026
29.9Answer Correctness Rate
8
Feb 26, 2026
48.46Pass@16
8
Feb 26, 2026
14.36Throughput
8
Feb 26, 2026
12.67Throughput
8
Feb 26, 2026
35.8Pass@1
8
Feb 26, 2026
82.1Accuracy
8
Feb 26, 2026
80.9Pass@1 Accuracy
8
Feb 26, 2026
63.9Pass@1
8
Feb 26, 2026
0.923Pass@1
8
Feb 26, 2026
100Pass@1
8
Feb 26, 2026
0.598Pass@1
8
Feb 26, 2026
57.2Accuracy
8
Feb 26, 2026
62.66Accuracy
8
Feb 26, 2026
14.71Pass@1
8
Feb 26, 2026
19.23Pass@1
8
Feb 26, 2026
0.185Pass@1
8
Feb 26, 2026
26.95Pass@1
8
Feb 26, 2026
62.2Pass@1
8
Feb 26, 2026