Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.51Pass@3
4
Mar 24, 2026
98.04pass@1
4
Mar 24, 2026
96.4Pass@1
4
Mar 24, 2026
100pass@1
4
Mar 24, 2026
97.1pass@1
4
Mar 24, 2026
100pass@1
4
Mar 24, 2026
97.8Pass@1
4
Mar 24, 2026
100pass@1
4
Mar 24, 2026
53.7Pass@1
4
Mar 17, 2026
100Success Rate (SR)
4
Mar 10, 2026
54.6MBPP Score
4
Mar 6, 2026
26.4Avg@8
4
Feb 26, 2026
33.7Avg@8
4
Feb 26, 2026
17.9Avg@8
4
Feb 26, 2026
9.76Throughput (tokens/s)
4
Feb 26, 2026
85Pass Rate
4
Feb 26, 2026
10.57Accuracy
4
Feb 26, 2026
99F1 Score
4
Feb 26, 2026
71.95HumanEval Score
4
Feb 26, 2026
60.65Pass@1
4
Feb 26, 2026
25.19Pass@1
4
Feb 26, 2026
83.75ASRs
4
Feb 26, 2026
84.7Pass@80
4
Feb 26, 2026
76.83pass@10
3
Jul 3, 2026
60.4Pass@10
3
Jul 3, 2026