Benzi, a new code-intelligence harness, resolved 78.2% of 500 real issues on SWE-bench Verified at under 10 cents per fix, according to benchmarks published on the project's site. In a 24-bug, 10-lang…
Benzi, a new code intelligence infrastructure for frontier AI models, claims to reduce source code reading by 56% compared to Claude Code Sonnet, achieving 78.2% on SWE-bench Verified for under 10 cen…
Benzi, a coding agent that compiles codebases into a resolved map instead of reading raw files, achieved a 45.5% pass rate on SWE-bench Verified (500 instances, one attempt each) using DeepSeek v4-fla…
Benzi, a coding harness framework, uses compiled codebase maps and static analysis checks to navigate code across ten languages, with real runtime hooks overlaying static analysis rather than dumping …
Benzi, a new AI coding assistant that combines a compiler, runtime tracer, harness, and AI agent to understand code from the ground up, was released on Hacker News. It challenges traditional RAG and e…