A new reference model for machine learning-driven materials discovery
© iStock
Researchers in the EPFL School of Engineering's Laboratory of Computational Science and Modeling (COSMO), led by Michele Ceriotti, have reached a significant milestone in material science: they have reached the top position on Matbench Discovery, the leading benchmarking platform for machine-learning interatomic potentials.
Beyond setting a new performance reference, the result highlights a thoughtful approach aimed at making machine learning more reliable and useful for scientific research. The Matbench Discovery leaderboard has long been dominated by models developed at Meta, which can deploy huge computational resources to train them.
The achievement of reaching the top position was made possible by the new model PET-OAM-XL: the latest evolution of a line of research that began with PET-MAD, whose foundational paper was recently published. PET-MAD was conceived as a lightweight, general-purpose model designed for advanced materials simulations, particularly molecular dynamics and other scenarios where robustness and scalability matter. PET-OAM-XL builds on this foundation by scaling the architecture and training it on datasets more specifically tailored to materials discovery tasks.
Read the full article on this work published by the EPFL AI Center.
Bigi, F., Pegolo, P., Mazitov, A., & Ceriotti, M. (2026). Pushing the limits of unconstrained machine-learned interatomic potentials. arXiv preprint arXiv:2601.16195.
Mazitov, A., Bigi, F., Kellner, M. et al. PET-MAD as a lightweight universal interatomic potential for advanced materials modeling. Nat Commun 16, 10653 (2025).
The PET-OAM-XL model on Matbench Discovery : https://matbench-discovery.materialsproject.org/models/pet-oam-xl-1.0.0
COSMO lab GitHub repository: https://github.com/lab-cosmo/upet
Funding & Support
Swiss National Supercomputing Centre (CSCS)
NCCR Marvel
EPFL AI Center
Swiss AI Initiative