Multi-agent swarms buy speed, not compute savings: same performance costs about twice the tokens
An analysis of OpenAI's charts finds scaling agent count buys capability less efficiently than longer chains of thought; its value is speed, and the numbers are first-party readings.
Original event 2026-09-21
Read from OpenAI's own charts, multi-agent parallelism mainly buys speed, not compute savings.
Writing on LessWrong, Toby Ord analyzed the GPT 5.6 launch-page charts: at equal performance, a 4-agent swarm uses roughly twice the total tokens of a single agent, and a 16-agent swarm roughly twice that again. His derived parallelizability parameter lambda falls between about 0.48 and 0.68, depending on the task.
That means scaling the swarm buys capability more expensively than lengthening a single agent's chain of thought; the payoff is speed, roughly 2x speed for 2x cost. Note this is a blogger's reading of vendor charts, with regressions run by Claude Opus 5, not an independent measurement.