Scaling agent swarms 10x yields only 3-5x the gain of 10x more tokens for one agent

tobyordoxford · x · 2026-09-22

Toby Ord estimates that scaling a swarm by 10x delivers only 10^λ — about 3x to 5x — of the performance gain from using 10x more tokens with a single agent. With λ estimated, one can convert between swarm scaling and scaling thinking duration, suggesting extending a single agent's thinking is far more efficient than adding agents.

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 →