AI in Chemistry: Study Highlights Strengths and Weaknesses

Computing power in the chemistry lab: Kevin Jablonka (left) and his team at HIPOLE Jena. Photo: Renzo Paulus

Computing power in the chemistry lab: Kevin Jablonka (left) and his team at HIPOLE Jena. Photo: Renzo Paulus

How well does artificial intelligence perform compared to human experts? A research team at HIPOLE Jena set out to answer this question in the field of chemistry. Using a newly developed evaluation method called “ChemBench,” the researchers compared the performance of modern language models such as GPT-4 with that of experienced chemists. 

The study has recently been published in the journal Nature Chemistry (DOI 10.1038/s41557-025-01815-x).

More than 2,700 chemistry tasks from research and education were tested—ranging from fundamental knowledge to complex problems. In areas such as reaction prediction or the analysis of large datasets, AI models often excelled with high efficiency. However, a critical weakness became apparent: the models also produced confident answers even when they were factually incorrect. Human chemists, by contrast, were more cautious and questioned their own assessments.

“Our study shows that AI can be a valuable tool—but it is no substitute for human expertise,” says Dr. Kevin M. Jablonka, lead author of the study. The findings offer important insights for the responsible use of AI in chemical research and education.

HIPOLE Jena (Helmholtz Institute for Polymers in Energy Applications Jena) is an institute of HZB in cooperation with Friedrich Schiller University Jena (FSU Jena).

ma

  • Copy link

You might also be interested in

  • Bright prospects for tin perovskite solar cells
    Science Highlight
    03.12.2025
    Bright prospects for tin perovskite solar cells
    Perovskite solar cells are widely regarded as the next generation photovoltaic technology. However, they are not yet stable enough in the long term for widespread commercial use. One reason for this is migrating ions, which cause degradation of the semiconducting material over time. A team from HZB and the University of Potsdam has now investigated the ion density in four different, widely used perovskite compounds and discovered significant differences. Tin perovskite semiconductors produced with an alternative solvent had a particular low ion density — only one tenth that of lead perovskite semiconductors. This suggests that tin-based perovskites could be used to make solar cells that are not only really environmentally friendly but also very stable.

  • Synchrotron radiation sources: toolboxes for quantum technologies
    Science Highlight
    01.12.2025
    Synchrotron radiation sources: toolboxes for quantum technologies
    Synchrotron radiation sources generate highly brilliant light pulses, ranging from infrared to hard X-rays, which can be used to gain deep insights into complex materials. An international team has now published an overview on synchrotron methods for the further development of quantum materials and technologies in the journal Advanced Functional Materials: Using concrete examples, they show how these unique tools can help to unlock the potential of quantum technologies such as quantum computing, overcome production barriers and pave the way for future breakthroughs.
  • Joint Kyiv Energy and Climate Lab goes live
    News
    28.11.2025
    Joint Kyiv Energy and Climate Lab goes live
    Helmholtz-Zentrum Berlin and the National University of Kyiv-Mohyla Academy established on 27 November a Joint Energy and Climate Lab.