Researchers from University College London and UNESCO conducted a study to assess how large language models (LLMs) handle climate change information. The study evaluated responses to various prompts, including simple factual questions and more complex interactions where users challenge the answers. A total of 33 models were analyzed, including notable ones like Claude Fable 5 and GPT-5.6 Sol. The findings aim to shed light on the accuracy and reliability of LLMs in providing climate-related information.
Key facts
- The study was conducted by University College London and UNESCO.
- It evaluated 33 large language models.
- Models included Claude Fable 5 and GPT-5.6 Sol.
- The research focused on responses to climate change queries.
- It analyzed both factual questions and user interactions.
A short AI summary in our own words. The reporting belongs to Ars Technica; we don't reproduce it.