Exploring the expertise of large language models in materials science and metallurgical engineering

This study establishes a performance baseline for 15 LLMs on materials science tasks using the MaScQA benchmark, paving the way for AI-driven advancements in materials discovery and analysis.

Materials Science Engineering Computer Science Physics

Paper

Similar papers

MatTools: Benchmarking Large Language Models for Materials Science ToolsSiyu Liu, Jiamin Xu, Beilin Ye et al.2025 · arXiv.org · 12 citations In Library

MaScQA: investigating materials science knowledge of large language modelsMohd Zaki, Jayadeva, Mausam Mausam et al.2023 · Digital Discovery In Library

MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and KnowledgeJerry Junyang Cheung, Shiyao Shen, Yuchen Zhuang et al.2025 · arXiv.org · 5 citations In Library

What do Large Language Models know about materials?Adrian Ehrenhofer, Thomas Wallmersperger, G. Cuniberti2025 · Advanced Engineering Materials · 1 citation In Library

A prompt-engineered large language model, deep learning workflow for materials classificationSiyu Liu, Tongqi Wen, A. S. L. Subrahmanyam Pattamatta et al.2024 · Materials Today · 46 citations In Library

Large language models in materials science and the need for open-source approachesFengxu Yang, Weitong Chen, Jack D. Evans2025 · Digital Discovery · 0 citations In Library

MatQnA: A Benchmark Dataset for Multi-modal Large Language Models in Materials Characterization and AnalysisY. Weng, Liqiang Gao, Lin Zhu et al.2025 · arXiv.org · 2 citations In Library

Are LLMs Ready for Real-World Materials Discovery?Santiago Miret, N. Krishnan2024 · arXiv.org · 62 citations In Library

Foundational Large Language Models for Materials ResearchVaibhav Mishra, Somaditya Singh, Dhruv Ahlawat et al.2024 · arXiv.org · 30 citations In Library

Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyLuca Foppiano, G. Lambard, Toshiyuki Amagasa et al.2024 · Science and Technology of Advanced Materials: Methods · 45 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal