Skip to content

Evaluation

CBRN information risk evaluation

Assessment of Gemini responses to adversarial CBRN questions: human-evaluated open questions (biological, radiological, nuclear) and closed-ended knowledge questions (chemical)

Biological & chemical risks Google DeepMind — Gemini

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Gemini 1.0
Google DeepMind — Gemini

rich detail 9 method fields published

See how this test was run