Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.6Accuracy
37
May 27, 2026
76.71Pass@1
36
Jul 7, 2026
48Solve Rate
36
Jul 3, 2026
41.6Pass@1 Accuracy
36
Jun 23, 2026
91.39Overall Score
36
Jul 1, 2026
69.44Pass@1
36
Jul 7, 2026
68.8Accuracy
36
Apr 6, 2026
81.13Pass@1
36
Feb 26, 2026
89.7Easy Accuracy
36
Mar 10, 2026
56.3Introductory Score
36
Jun 23, 2026
69.9Accuracy
35
Apr 23, 2026
66.17MBPP Score
35
Feb 26, 2026
4,062Generation Speed
34
Jun 30, 2026
88.3Pass@1
34
May 28, 2026
54.9OlmoBaseEval Code Score
34
Apr 7, 2026
4.28Spd
33
Apr 3, 2026
73.8Avg@16 Accuracy
33
Jun 9, 2026
75.6Pass@1
33
Jun 4, 2026
68.9Pass@1
33
May 13, 2026
86.6Accuracy
32
Jun 23, 2026
35.6MBPP Score
32
Apr 16, 2026
87.2Eval+ Score
32
Mar 20, 2026
88.5pass@1
32
Jun 4, 2026
81.95Pass Rate
32
Feb 27, 2026
58Accuracy
32
Feb 26, 2026