ArticleNature chemistry2025
A framework for evaluating the chemical knowledge and reasoning abilities of large language models against the expertise of chemists.
Article in Nature chemistry, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 27 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
27 citing papers in PubMed.
- Chemical language models for early-stage drug discovery: applications, pitfalls, and future directions.Journal of computer-aided molecular design · 2026Review
- The automated red pen.Nature reviews. Chemistry · 2026Article
- Transforming Molecular Synthesis With Large Language Models.Chemistry (Weinheim an der Bergstrasse, Germany) · 2026Review
- AI-Driven Data Extraction and AGREE-Based Greenness Evaluation of Analytical Methods for Natural Products: Insights from Selected Studies.Analytical chemistry · 2026Article
- Automating Chemical Reasoning in High-Throughput Phase Identification With a Probabilistic, LLM-Guided Framework.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Leveraging Large Language Models for Understanding Fundamental Principles of Catalysis.The journal of physical chemistry. C, Nanomaterials and interfaces · 2026Review
- Digital Reticular Chemistry: How Artificial Intelligence is Redefining Covalent Organic Framework Research.JACS Au · 2026Review
- Text-to-flowsheet: an LLM-assisted pipeline for expert-level digitization and automated simulation of chemical processes.Digital discovery · 2026Article
- Looking back and to the future after four-plus years of language in chemistry.Digital discovery · 2026Review
- Can You Help ChatGPT Get an "A" in Organic Chemistry? Teaching Effective Prompting of Large Language Models for Reaction Prediction.Journal of chemical education · 2026Article
- A light-weight Graph Neural Network for the prediction ofJournal of cheminformatics · 2026Article
- General-Purpose Models for the Chemical Sciences: LLMs and Beyond.Chemical reviews · 2026Review
- PredictingACS omega · 2026Article
- Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Data set Generation for Training Machine-Learned Interatomic Potentials.Journal of chemical theory and computation · 2026Article
- Assessing the Chemical Intelligence of Large Language Models.Journal of chemical information and modeling · 2026Article
- Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials.ACS applied materials & interfaces · 2025Article
- Evaluating large language models on multimodal chemistry olympiad exams.Communications chemistry · 2025Article
- Fluorine-Free Ion Exchange Membranes for (Photo)electrochemical Applications.ACS polymers Au · 2025Review
- MOF-ChemUnity: Literature-Informed Large Language Models for Metal-Organic Framework Research.Journal of the American Chemical Society · 2025Article
- Assay2Mol: Large Language Model-based Drug Design Using BioAssay Context.Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
35 authors.
Funding
Abstract
Large language models (LLMs) have gained widespread interest owing to their ability to process human language and perform tasks on which they have not been explicitly trained. However, we possess only a limited systematic understanding of the chemical capabilities of LLMs, which would be required to improve models and mitigate potential harm. Here we introduce ChemBench, an automated framework for evaluating the chemical knowledge and reasoning abilities of state-of-the-art LLMs against the expertise of chemists. We curated more than 2,700 question-answer pairs, evaluated leading open- and closed-source LLMs and found that the best models, on average, outperformed the best human chemists in our study. However, the models struggle with some basic tasks and provide overconfident predictions. These findings reveal LLMs' impressive chemical capabilities while emphasizing the need for further research to improve their safety and usefulness. They also suggest adapting chemistry education and show the value of benchmarking frameworks for evaluating LLMs in specific domains.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.