MatBench

MatBench is a benchmark dataset that contains a variety of tasks used to evaluate the performance of machine learning models in materials science, specifically in the context of computational catalysis.

Papers using MatBench (9)

Leveraging neural network interatomic potentials for a foundation model of chemistry2025 · 9 citesAutonomous Computational Catalysis Research via Agentic Systems2026 · 2 citesCombining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability2025 · 4 citesReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction2025 · 1 citesEnhancing composition-based materials property prediction by cross-modal knowledge transfer2025Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction2025From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction2023 · 22 citesConnectivity Optimized Nested Graph Networks for Crystal Structures2023 · 9 citesStructure to Property: Chemical Element Embeddings and a Deep Learning Approach for Accurate Prediction of Chemical Properties2023 · 3 cites