Get the latest tech news

Qodo CLI agent scores 71.2% on SWE-bench Verified

Read about Qodo Command scores 71.2% on SWE-bench Verified in our blog.

Thanks to a strong partnership with Anthropic—Qodo is a “ Powered by Claude ” solution, we’re collaboratively building the world’s most adaptive and learning-oriented coding agents, leveraging one of the most advanced language models available today. Qodo Command solves this by distilling multi-layered code into precise, high-signal summaries—ensuring that language models receive only the most relevant, structured context at every step. Shell Tool: executing like a real developer, Qodo agents can interact with the system shell to run build scripts and linters, execute test suites and validate hypotheses in real-time Ripgrep: for deep codebase understanding, Qodo Command is natively designed for optimized usage of ripgrep recursive search tool to locate relevant code across large repositories Sequential Thinking: structured agent reasoning helped contribute to the benchmark results by breaking down tasks into actionable steps.

Get the Android app