AnalysisAI ModelsNovember 19, 2026

UNESCO-led study tests 33 LLMs on climate science accuracy

Read original source →arstechnica.com

Flagship models scored around 78% on the hardest questions — how confident climate scientists are in IPCC conclusions. The UCL/UNESCO study ran 600 questions across 33 models, including Claude Fable 5, Claude Opus 5, Gemini 3.1 Pro Preview, Gemini 3.6 Flash and GPT-5.6 Sol.

1 source

More stories today

Open the live feed