Gemini 2.5
Google DeepMind — Gemini
rich detail 14 method fields published
Evaluation
Frontier Safety Framework (FSF) evaluations comparing test results against CCLs and internal early-warning alert thresholds across four risk domains: CBRN, cybersecurity, ML R&D, deceptive alignment
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.
rich detail 14 method fields published