Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Coding on AInstein-SWE-Bench
Loading...
42.8
Pass@1
Gemini 3-pro
18.36
24.705
31.05
37.395
Mar 21, 2026
Pass@1
Updated 25d ago
Evaluation Results
Method
Method
Links
Pass@1
Gemini 3-pro
2026.03
42.8
Seed1.8
2026.03
36.7
GPT-5 High
2026.03
35.4
Claude Sonnet-4.5
2026.03
33.7
Gemini 2.5-pro
2026.03
19.3
Feedback
Search any
task
Search any
task