To match a 100x single-agent token scale-up, a swarm needs 900x-15,000x more agents

tobyordoxford · x · 2026-09-22

Toby Ord quantifies why swarms rarely pay off: a 4-agent swarm uses 2x total tokens but only 0.5x per agent, so it can run up to 2x faster (never quite reaching that in practice). The catch compounds at scale — matching the performance gain of a 100x token scale-up for a single agent requires growing the swarm by 900x to 15,000x, and the gap widens further with larger scale-ups. Swarms buy speed, not performance.

Related event: Toby Ord quantifies swarm scaling: far less efficient than longer chain-of-thought(17 posts)→

Original post →

More from coding & agent

coding & agent channel →