The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models

Dataset

LICENSE: The OMol25 dataset is provided under a CC-BY-4.0 license

Download links and instructions on how to access the data can be found here.

Model checkpoints

LICENSE: OMol25 model checkpoints are provided under the FAIR Chemistry License

Baseline model checkpoints trained on the full OMol25 dataset are provided below.

Name	Split	Checkpoint
eSEN-sm-direct	All	esen_sm_direct_all.pt
eSEN-sm-conserving	All	esen_sm_conserving_all.pt
eSEN-md-direct	All	esen_md_direct_all.pt
eSEN-lg-direct	All	coming soon...
AllScAIP-md-direct	All	AllScAIP-md-direct.pt
AllScAIP-md-conserving	All	AllScAIP-md-conserving.pt

Open Polymers 2026 (OPoly26) Dataset

LICENSE: The OPoly26 dataset is provided under a CC-BY-4.0 license

The OPoly26 dataset is an extension of OMol25 focusing specifically on polymers. The DFT settings are identical between OMol25 and OPoly26, so the two can be mixed without worrying about inconsistencies between settings.

Download links and instructions on how to access the data can be found here.

How to use

Model checkpoints can be readily used in the fairchem repo using our custom ASE-calculator. You can find details about using the model, along with other utilities including tutorials and documentation in the official fairchem repo.

Leaderboard

The OMol25 leaderboard can be found here to help evaluate and track community progress.

Support

If you run into any issues feel free to post your questions or comments on Github Issues.

Citation

If you use this work, please cite:

@misc{levine2025openmolecules2025omol25,
      title={The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models}, 
      author={Daniel S. Levine and Muhammed Shuaibi and Evan Walter Clark Spotte-Smith and Michael G. Taylor and Muhammad R. Hasyim and Kyle Michel and Ilyes Batatia and Gábor Csányi and Misko Dzamba and Peter Eastman and Nathan C. Frey and Xiang Fu and Vahe Gharakhanyan and Aditi S. Krishnapriyan and Joshua A. Rackers and Sanjeev Raja and Ammar Rizvi and Andrew S. Rosen and Zachary Ulissi and Santiago Vargas and C. Lawrence Zitnick and Samuel M. Blau and Brandon M. Wood},
      year={2025},
      eprint={2505.08762},
      archivePrefix={arXiv},
      primaryClass={physics.chem-ph},
      url={https://arxiv.org/abs/2505.08762}, 
}

If you use OPoly26, please cite:

@misc{levine2025openpolymers2026opoly26,
      title={The Open Polymers 2026 (OPoly26) Dataset and Evaluations}, 
      author={Daniel S. Levine and Nicholas Liesen and Lauren Chua and James Diffenderfer and Helgi Ingolfsson and Matthew P. Kroonblawd and Nitesh Kumar and Amitesh Maiti and Supun S. Mohottalalage and Muhammed Shuaibi and Brian Van Essen and Brandon M. Wood and C. Lawrence Zitnick and Samuel M. Blau and Evan R. Antoniuk},
      year={2025},
      eprint={2512.23117},
      archivePrefix={arXiv},
      primaryClass={physics.chem-ph},
      url={https://arxiv.org/abs/2512.23117}, 
}

facebook/OMol25