Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Autonomous Task Completion on GitHub
Loading...
84
Success Rate
Github + GitLab (PolySkill)
66.008
70.679
75.35
80.021
Oct 17, 2025
Success Rate
Skill Usage
Updated 3mo ago
Evaluation Results
Method
Method
Links
Success Rate
Skill Usage
Github + GitLab (PolySkill)
Training Setting=Self-...
2025.10
84
39.5
Github
Training Setting=Singl...
2025.10
81.5
54.1
Gitlab → Github
Training Setting=Seque...
2025.10
80.1
51.9
Github → GitLab
Training Setting=Seque...
2025.10
77.8
48.6
GitLab
Training Setting=Singl...
2025.10
71.5
12.8
Baseline
Iters=–
2025.10
66.7
-
Feedback
Search any
task
Search any
task