Cursor's Agent Swarm: Cheaper Models Handle Most Coding When Frontier Models Plan
The Decoder 2 months ago 13
Cursor built an agent swarm system that separates cheaper worker models from expensive frontier models used for planning, achieving 1,000 commits per second by dividing cognitive context between roles. In a Rust SQLite implementation benchmark, the hybrid approach (Opus planner with Composer 2.5 workers) scored 73–100 percent while costing $1,339 total, compared to $10,565 for GPT-5.5 running solo at similar quality. By using cheaper models for execution after frontier models establish plans, Cursor reduced codebase sizes by up to 85 percent and cut worker costs from $9,373 to $411 at comparable performance.