Show HN: Benzi – A Code Intillegence/Harness Beating Claude Code and CodeGraph
The article presents a performance comparison between the 'Benzi' code intelligence harness and other mainstream AI coding tools. Using SWE-bench data, it claims Benzi achieves higher resolution rates for GitHub issues while maintaining lower operational costs and resource usage.
Why it matters
Provides developers and startups with comparative data on AI coding assistants, influencing tool selection for software engineering workflows.
Apples to apples comparison: Benzi harness vs mainstream harnesses, 24 GitHub issues, 10 languages.
Benzi harness on SWE-bench Verified. 78.2% of 500 real issues resolved at under 10 a fix.
Apples to Apples comparison: Code Graph's code intelligence vs Benzi's AI-native code intelligence
Every task, every attempt, verbatim - nothing held back.
Learn more about Benzi: benzi.fly.dev/about
Every harness opens more source as bugs get harder. The question is the slope. Each point is one bug; the 24 are laid out easiest to hardest, left to right.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in