Gemini 2.5
Google DeepMind — Gemini
rich detail 9 method fields published
Evaluation
External autonomous systems risk evaluation (deception, scheming, sabotage)
External group tests of model ability and propensity to covertly pursue misaligned goals: strategic deception, in-context scheming reasoning, and sabotage capabilities (compromising other language models)
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.