ChemBench: Are large language models superhuman chemists?
Active
ChemBench is designed to reveal limitations of current frontier models for use in the chemical sciences. It consists of 2786 question-answer pairs compiled from diverse sources. Our corpus measures reasoning, knowledge and intuition across a large fraction of the topics taught in
- Publisher
- Friedrich Schiller University Jena
- Domain
- Knowledge
- License
- mit
- Published
- Aug 2025
- Notable for
- Benchmark for evaluating Knowledge.
Cite
Notes
Only stored in your browser.
FAQ
- What is ChemBench: Are large language models superhuman chemists??
- ChemBench is designed to reveal limitations of current frontier models for use in the chemical sciences. It consists of 2786 question-answer pairs compiled from diverse sources. Our corpus measures reasoning, knowledge and intuition across a large fraction of the topics taught in
- What license is ChemBench: Are large language models superhuman chemists? under?
- ChemBench: Are large language models superhuman chemists? is available under mit.