Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Software Engineering Issue Resolution on SWE-bench 500 (test)
Loading...
72.2
Resolution Score
agyn
64.712
66.656
68.6
70.544
Feb 1, 2026
Resolution Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Resolution Score
agyn
Model=GPT-5 / GPT-5-co...
2026.02
72.2
OpenHands
Model=GPT-5
2026.02
71.8
mini-SWE-agent
Model=GPT-5.2, Reasoni...
2026.02
71.8
mini-SWE-agent
Model=GPT-5, Reasoning...
2026.02
65
Feedback
Search any
task
Search any
task