Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on BigCodeBench (Pass@1, Pass@3)
Loading...
65.1
Pass@1
SkillTTA
40.348
46.774
53.2
59.626
May 16, 2026
Pass@1
Pass@3
Updated 2mo ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@3
SkillTTA
Skill Synthesis Model=...
2026.05
65.1
67.3
SkillTTA
Skill Synthesis Model=...
2026.05
60.6
66.4
Trace2Skill
Skill Synthesis Model=...
2026.05
53.5
61.1
Trace2Skill
Skill Synthesis Model=...
2026.05
51.7
58.2
ReAct
Skill Synthesis Model=...
2026.05
50.3
56.4
Zero-shot
Skill Synthesis Model=...
2026.05
48.9
55.8
MemRL
Skill Synthesis Model=...
2026.05
41.3
47
Feedback
Search any
task
Search any
task