# An open benchmark for machine learning-based polymer property prediction

arXiv: https://arxiv.org/abs/2609.27036 · HTML: https://mlsanity.com/paper/2609.27036/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 45 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics](https://mlsanity.com/paper/2209.14803/) (2022)
- [Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions](https://mlsanity.com/paper/2308.14920/) (2023)
- [Polymer Informatics with Multi-Task Learning](https://mlsanity.com/paper/2010.15166/) (2020)
- [Polymer Informatics: Current Status and Critical Next Steps](https://mlsanity.com/paper/2011.00508/) (2020)
- [A graph representation of molecular ensembles for polymer property prediction](https://mlsanity.com/paper/2205.08619/) (2022)
- [Inverse Design of Copolymers Including Stoichiometry and Chain Architecture](https://mlsanity.com/paper/2410.02824/) (2024)
- [Representing Polymers as Periodic Graphs with Learned Descriptors for Accurate Polymer Property Predictions](https://mlsanity.com/paper/2205.13757/) (2022)

## Abstract (arXiv)

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.