Toby Ord re-draws OpenAI's swarm scaling data: 4x agents cost ~2x tokens

tobyordoxford · x · 2026-09-22

Researcher Toby Ord re-analyzed OpenAI's multi-agent swarm scaling graphs, which lacked a clean control fixing CoT length while scaling agent count. By re-plotting with a log x-axis and joining points with equal tokens-per-agent, he shows all swarm sizes scale logarithmically with the same slope, and every 4x increase in agents costs roughly 2x total tokens.

Related event: Oxford's Toby Ord quantifies swarm scaling: far less compute-efficient than longer thinking(17 posts)→

Original post →

More from Research

Research channel →