Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
7,927Pass@1
1,048
Jun 4, 2026
100Pass@1
701
Jul 7, 2026
95.1Pass@1
411
Jul 3, 2026
100Pass@1
393
May 29, 2026
96.95pass@1
329
Jun 29, 2026
85.75Accuracy
243
Jun 15, 2026
98.7Accuracy
242
Feb 26, 2026
84.39Pass@1
238
Jun 1, 2026
97.56Accuracy
224
Jun 4, 2026
98.27Accuracy
212
Jun 19, 2026
92.4Pass@1
211
May 22, 2026
89.1Pass@1
193
Mar 16, 2026
94.1Pass@1
171
Mar 23, 2026
79.8Accuracy
165
May 25, 2026
8.22Speedup Factor
147
May 29, 2026
92.2Accuracy (%)
146
Feb 26, 2026
85.4Pass@1
145
Feb 26, 2026
95.22HumanEval Score
140
Jun 19, 2026
98.1Pass@1
132
May 28, 2026
86Pass@1
122
Jul 3, 2026
89Pass@1
118
Jun 12, 2026
91.2Pass@1
111
May 18, 2026
89.6Pass@1
108
May 8, 2026
57.93Accuracy
100
Jun 26, 2026
8.99Average Acceptance Length (τ)
95
Jul 1, 2026