Cursor Agents Rebuild SQLite from 835-Page Manual, Cost Varies 15x by Model Mix

StanfordAILab · x · 2026-07-21

A team of agents from Cursor successfully rebuilt SQLite in Rust using only its 835-page manual, without access to a reference executable. \n\nThe replica managed to pass 100% of a held-out test suite. Interestingly, the team noted a 15x variance in cost depending on the mix of models used. This provides a compelling case study for multi-agent effects using recent long-horizon coding benchmarks like ProgramBench.

Related event: Cursor Multi-Agent Rebuilds SQLite in Rust, Model Mix Cuts Cost 15x(8 posts)→

Original post →

More from coding & agent

coding & agent channel →