Sreekanth Kunchapu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Sreekanth Kunchapu has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Abdelrahman Ibrahim
Laboratory of Organic and Macromolecular Chemistry, Friedrich Schiller University Jena, Jena, Germany
1 shared publication - Adrian Mirza
Helmholtz-Zentrum Berlin für Materialien und Energie GmbH, Berlin, Germany
1 shared publication - Akassong Dominique Dinga Wonanke
School of Science and Technology, Nottingham Trent University, Clifton Lane, Nottingham, NG11 8NS, UK
1 shared publication - Amir Mohammad Elahi
Laboratory of Molecular Simulation, Institut des Sciences et Ingenierie Chimiques, École Polytechnique Fédérale de Lausanne, Sion, Switzerland
1 shared publication - Anagha Aneesh
Laboratory of Organic and Macromolecular Chemistry (IOMC) Friedrich Schiller University Jena Humboldtstrasse 10 07743 Jena Germany
1 shared publication - Aswanth Krishnan
QpiVolta Technologies Pvt Ltd, Bengaluru, India
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 20 May 2025
- Published by Springer Nature in Nature Chemistry
- Vol. 17 (7) , 1027-1034
A framework for evaluating the chemical knowledge and reasoning abilities of large language models against the expertise of chemists
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.
- 20 May 2025
- Published by Springer Nature in Nature Chemistry
- Vol. 17 (7) , 1027-1034
Top Cited PapersOpen AccessA framework for evaluating the chemical knowledge and reasoning abilities of large language models against the expertise of chemists
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.