metaai·lightalo unofficial · independent
Universe / AI for Science / Open Materials 2024
AI for Science · 2024

Open Materials 2024

Open Materials 2024 (OMat24)

Open data that topped Matbench Discovery for predicting stable crystals

open source EquiformerV2 31M / 86M / 153M; eSEN 30M params

Latest: OMat24 (October 2024); successor capabilities folded into UMA

An open inorganic-materials dataset of over 100 million DFT calculations plus pretrained EquiformerV2-based interatomic potentials, released October 2024. The models set state-of-the-art results on the Matbench Discovery leaderboard for predicting stable materials, and the permissively licensed dataset became a foundation for the materials-discovery ML community.

Why it matters

Over 100 million inorganic DFT calculations plus pretrained potentials that took the top of the Matbench Discovery leaderboard for predicting stable materials. Released under a permissive license, it became a foundation dataset for materials-discovery ML, and its capabilities were folded into UMA.

Facts

Try it yourself

Lineage

Descends fromOpen Catalyst Project
Led toUMA — Universal Models for Atoms

See the whole family tree →

Sources

More in AI for Science

fairchemOpen Molecules 2025Brain2QwertyOpenDAC / ODAC25Brain & AI: Decoding Perception from MEG/EEGESM / ESMFold

Read the AI for Science story on the sky →

✦ Open on the map Explore AI for Science Quiz me