27B agent Faraday beats Claude Opus 4.8 and GPT-5.5 on research replication via new Replica method

omarsar0 · x · 2026-08-15

A new study introduces Replica, a method that turns paper replication into a scalable RL task space, and trains a 27B-parameter agent called Faraday that outperforms Claude Opus 4.8 and GPT-5.5 on held-out research replication tasks.

Paper link included.

Related event: Inherent Labs' 27B AI Scientist Faraday Beats Claude Opus 4.8 and GPT-5.5 at Paper Reproduction(6 posts)→

Original post →

More from coding & agent

coding & agent channel →