Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Coding on Multi-SWE-Bench
Loading...
44.3
Pass@1
Claude Sonnet-4.5
19.756
26.128
32.5
38.872
Mar 21, 2026
Pass@1
Updated 25d ago
Evaluation Results
Method
Method
Links
Pass@1
Claude Sonnet-4.5
2026.03
44.3
Gemini 3-pro
2026.03
42.7
Seed1.8
2026.03
42
GPT-5 High
2026.03
41.7
Gemini 2.5-pro
2026.03
20.7
Feedback
Search any
task
Search any
task