The cost of thinking is similar between large reasoning models and humans

Read the full article See related articles

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Do neural network models capture the cognitive demands of human reasoning? Across four reasoning domains, we show that the length of the chain-of-thought generated by a large reasoning model predicts human reaction times both within tasks—tracking item-level difficulty—and across tasks—capturing broader differences in cognitive demands. This model-to-human alignment shows that reasoning models mirror core features of problem and task complexity in human cognition.

Article activity feed