Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Software Engineering on SWE-Bench Pro (public)
Loading...
59
Resolve Rate (Pass@1)
CCA
42.048
46.449
50.85
55.251
Dec 11, 2025
Resolve Rate (Pass@1)
Updated 4d ago
Evaluation Results
Method
Method
Links
Resolve Rate (Pass@1)
CCA
Backbone Model=GPT-5.2
2025.12
59
OpenAI
Backbone Model=GPT-5.2
2025.12
56
CCA
Backbone Model=Claude...
2025.12
54.3
CCA
Backbone Model=Claude...
2025.12
52.7
Anthropic
Backbone Model=Claude...
2025.12
52
Live-SWE-Agent
Backbone Model=Claude...
2025.12
45.8
CCA
Backbone Model=Claude...
2025.12
45.5
SWE-Agent
Backbone Model=Claude...
2025.12
43.6
SWE-Agent
Backbone Model=Claude...
2025.12
42.7
Feedback
Search any
task
Search any
task