Benzi coding agent reads less source, hits 78.2% on SWE-bench
Open-source project Benzi takes a counterintuitive approach to coding agents: read as little source code as possible. By leveraging compiler-based intelligent localization instead of pulling code snippets or embedding retrieval, it cuts token bloat and reaches 78.2% on SWE-bench.
2026-08-28 ~ 2026-08-28 · 2 related posts
- Benzi: coding agent that reads less source, hits 78.2% SWE-bench under 10¢ a fix — DonkeyTheKing · 2026-08-28
- Benzi coding agent reads less source code, hits 78.2% on SWE-bench for under 10 cents a fix — DonkeyTheKing · 2026-08-28