Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
42.07Pass@1
6
Apr 9, 2026
68.3Avg@64
6
Apr 7, 2026
86.2pass@1
6
Apr 3, 2026
39.6Accuracy
6
Apr 2, 2026
61.7Accuracy
6
Apr 2, 2026
57.2Accuracy
6
Apr 2, 2026
77Score
6
Mar 17, 2026
47.4CSR (%)
6
Mar 13, 2026
42.4Score
6
Mar 12, 2026
64.59Accuracy (%)
6
Mar 9, 2026
59.35Accuracy (%)
6
Mar 9, 2026
85.68Accuracy
6
Mar 4, 2026
92.68Accuracy
6
Mar 4, 2026
42Pass@1 (Lua)
6
Mar 4, 2026
172.25Throughput (tokens/s)
6
Mar 12, 2026
28.1Pass@1
6
Feb 26, 2026
81.4Pass@1
6
Feb 26, 2026
0.063Inference Cost (USD)
6
Feb 26, 2026
56.8Pass@1 Accuracy
6
Feb 26, 2026
25.6Accuracy
6
Feb 26, 2026
13.33Pass@1
6
Feb 26, 2026
13.33Pass@1
6
Feb 26, 2026
37.86Pass Rate
6
Feb 26, 2026
76.43Pass@1
6
Feb 26, 2026
1TPF
6
Feb 26, 2026