An open benchmark for machine learning-based polymer property prediction

Abstract

Polymer property prediction lacks open, standardized benchmarks that enable rigorous comparison of machine-learning methods, with existing resources covering only a narrow fraction of polymer architectures, such as homopolymers. We introduce Polymer Benchmark 2026 (PolyBench26), an open dataset comprising nearly 250,000 polymer-property datapoints across eight physical properties, including data from experimental measurements, density functional theory, and molecular dynamics. The benchmark supports four evaluation tasks across homopolymers and alternating, random, and block copolymers: in-distribution property prediction, dataset-size scaling, repeat-unit complexity, and transfer to held-out polymer architectures. We compare language model, graph-based, and descriptor-based approaches and find graph-based models provide the lowest errors in property prediction, retain their advantage across the evaluated training-set sizes, and remain robust to increasing repeat-unit complexity. PolyBench26 provides a reproducible foundation for developing models for the increasingly complex polymer design space. The PolyBench26 benchmark is available open-source at https://github.com/rlearsch/PolymerBenchmark2026.

Towards Multiscale Molecular Representation Learning through Geometry-Based Fragmentation for Polymer Property Prediction
Makoto Takamoto, Chaitanya Sampara, Viktor Zaverkin +2
arXiv5 Nov 2026PreprintarXiv licenceFull textPhysical chemistry Condensed matterarXiv
HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
Ge Sun, Gervasio Zaldivar, Yuan Tian +5
arXiv2 Sep 2026PreprintCC BY-NC-ND 4.0Full textPhysical chemistry Computational physicsarXiv
MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
Ryuhei Okuno, Nontawat Charoenphakdee, Kaoru Hisama +1
arXiv8 Sep 2026PreprintCC BY 4.0Full textPhysical chemistry Condensed matterarXiv
Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
Vladislav Korostelev, Pjotrs Žguns, Konstantin Klyukin
arXiv12 Oct 2026PreprintarXiv licenceFull textPhysical chemistry Computational physicsarXiv
Pressure-transferable universal machine-learning potentials: the WBM-MatPES benchmark and Tuga-FF
Pierre-Paul De Breuck, Thalis H. B. da Silva, Antoine Loew +2
arXiv10 Oct 2026PreprintCC BY 4.0Full textCondensed matterarXiv

Cite

BibTeX RIS

BibTeX

@misc{learsch2026open,
  title = {{An open benchmark for machine learning-based polymer property prediction}},
  author = {Robert W. Learsch and Nicholas Liesen and Daniel S. Levine and Anna M. Hiszpanski and Evan R. Antoniuk},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.27036},
  eprint = {2609.27036},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27036},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - An open benchmark for machine learning-based polymer property prediction
AU  - Robert W. Learsch
AU  - Nicholas Liesen
AU  - Daniel S. Levine
AU  - Anna M. Hiszpanski
AU  - Evan R. Antoniuk
PY  - 2026
DA  - 2026/09/22
PB  - arXiv
DO  - 10.48550/arxiv.2609.27036
UR  - https://arxiv.org/abs/2609.27036
AB  - Polymer property prediction lacks open, standardized benchmarks that enable rigorous comparison of machine-learning methods, with existing resources covering only a narrow fraction of polymer architectures, such as homopolymers. We introduce Polymer Benchmark 2026 (PolyBench26), an open dataset comprising nearly 250,000 polymer-property datapoints across eight physical properties, including data from experimental measurements, density functional theory, and molecular dynamics. The benchmark supports four evaluation tasks across homopolymers and alternating, random, and block copolymers: in-distribution property prediction, dataset-size scaling, repeat-unit complexity, and transfer to held-out polymer architectures. We compare language model, graph-based, and descriptor-based approaches and find graph-based models provide the lowest errors in property prediction, retain their advantage across the evaluated training-set sizes, and remain robust to increasing repeat-unit complexity. PolyBench26 provides a reproducible foundation for developing models for the increasingly complex polymer design space. The PolyBench26 benchmark is available open-source at https://github.com/rlearsch/PolymerBenchmark2026.
ER  -

Abstract

Related

Cite