Periodic Labs post-trains on real experiment data, beats GPT-6 Astra on XRD analysis

Tanishq Mathew Abraham, Ph.D. @iScienceLuvrOriginally posted 2026.09.16

Open original on X

Periodic Labs is doing extremely cool work applying frontier AI research to materials science. Here they post-train a model for a X-ray diffraction analysis, beating GPT-6 Astra and boosting performance of Kimi K2.6 by 20x! What's worth noting here is Periodic is doing RL directly with real-world experimental data, which comes with many unique challenges over coding/knowledge-work environments.

This post quotes another post: “OpenAI trains Neon materials model on 1,300 H200s, beating GPT-6 Astra on its own benchmark”