MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 12868-12879
Abstract
No abstract availableAll Related Versions
Funding Information
- Defense Advanced Research Projects Agency (HR001126CE054)
- NIH (National Institutes of Health) (OT2OD038003)
- NIH (National Institutes of Health) (U54OD036472)
- NIH (National Institutes of Health) (U54HG012517)
- NIH (National Institutes of Health) (U54DK097771)
- NSF (National Science Foundation) (2312501)
- NSF (National Science Foundation) (2106859)
This publication has 11 references indexed in Scilit:
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningNature, 2025
- MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI2024
- MM-PhyQA: Multimodal Physics Question-Answering with Multi-image CoT Prompting2024
- SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific ResearchProceedings of the AAAI Conference on Artificial Intelligence, 2024
- PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition2024
- Language Models can Solve Computer Tasks2023
- Learn to Explain: Multimodal Reasoning Via Thought Chains for Science Question Answering2022
- PlotQA: Reasoning over Scientific Plots2020
- Physical Metallurgy2010
- Fundamentals of Ceramics2003