Li–P–S Electrolyte Materials as a Benchmark for Machine-Learned Interatomic Potentials

Journal article

With the growing availability of machine-learned interatomic potential (MLIP) models for materials simulations, there is an increasing demand for robust, automated, and chemically informed benchmarking methodologies. In response, we here introduce LiPS-25, a curated benchmark data set for a canonical series of solid-state electrolyte materials from the Li2S–P2S5 pseudobinary compositional line, including crystalline and amorphous configurations. Together with the data set, we present a suite of performance tests that range from conventional numerical error metrics to physically motivated evaluation tasks. With a focus on graph-based MLIP architectures, we then show examples of using this data set to conduct numerical experiments, systematically assessing (i) the effect of hyperparameters on task-level performance and (ii) the fine-tuning behavior of selected pretrained (“foundational”) MLIP models. Beyond the Li–P–S solid-state electrolytes, we expect that such benchmarks and accompanying code can be readily adapted to other material systems.

Authors: Fragapane, NL; Deringer, VL

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: American Chemical Society
• Journal: Journal of Chemical Theory and Computation
• Volume: 22
• Issue: 7
• Pages: 3646-3659
• Publication date: 2026-03-18
• Acceptance date: 2026-02-04
• DOI: 10.1021/acs.jctc.5c02006
• EISSN: 1549-9626
• ISSN: 1549-9618
• Language: English
• Keywords: Benchmark (surveying); Benchmarking; Suite; Set (abstract data type); Focus (optics); Electrolyte; Hyperparameter; Range (aeronautics)