Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Code-Intensive Task Generation on GitHub Repositories
Loading...
50,137
Instances Count
SWE-smith
380.28
13,297.89
26,215.5
39,133.11
Feb 11, 2026
Instances Count
Updated 4d ago
Evaluation Results
Method
Method
Links
Instances Count
SWE-smith
Gold Instance=Pre-inst...
2026.02
50,137
SWE-Dev
Gold Instance=Pre-inst...
2026.02
14,000
R2E-Gym
Gold Instance=Pre-inst...
2026.02
8,135
SWE-Gym
Gold Instance=Pre-inst...
2026.02
2,438
SWE-Bench
Gold Instance=Pre-inst...
2026.02
2,294
Feedback
Search any
task
Search any
task