Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Engineering Tasks on SWE-rebench subset V2 (test)
Loading...
43.7
Resolved Rate
Claude Opus 4.6
37.044
38.772
40.5
42.228
Mar 29, 2026
Resolved Rate
Updated 19d ago
Evaluation Results
Method
Method
Links
Resolved Rate
Claude Opus 4.6
Scaffold=Claude Code
2026.03
43.7
KAT-Coder-V2
Scaffold=Claude Code
2026.03
43.3
KAT-Coder-V2
Scaffold=OpenCode
2026.03
38.7
Claude Opus 4.6
Scaffold=OpenCode
2026.03
37.3
Feedback
Search any
task
Search any
task