Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
2.96Speedup Ratio
24
Jul 1, 2026
88.4Avg@16 Score
24
Jun 9, 2026
74.8Pass@4
24
May 27, 2026
43.6Pass@4
24
May 27, 2026
74.7Pass@1
24
May 22, 2026
86.2pass@1
24
May 22, 2026
59.06Accuracy
24
May 19, 2026
94.05Accuracy
24
May 19, 2026
73.4r* Pass Rate
24
May 7, 2026
60.98Accuracy
24
Feb 26, 2026
3.52Speedup
24
Feb 26, 2026
3.23Speedup
24
Feb 26, 2026
47.25Accuracy (pass@1)
24
Feb 26, 2026
99.1Accuracy
24
May 21, 2026
22.6Pass@1
24
Jun 9, 2026
72.7Pass Rate
24
Feb 26, 2026
54.2MB+ Score
23
Jul 7, 2026
89.3Pass@4
23
May 26, 2026
86.7Eval+
23
Mar 20, 2026
96.79Accuracy
23
May 7, 2026
45.7Accuracy
23
Jun 1, 2026
34.9Accuracy
23
May 28, 2026
10.28Mean Acceptance Length (τ)
22
May 12, 2026
41.7Pass@1
22
Feb 26, 2026
24.89Avg@8
22
Feb 26, 2026