Gemini 1.0
Google DeepMind — Gemini
partial detail 5 method fields published
Evaluation
Child safety adversarial evaluation (Google Trust and Safety)
Adversarial prompts developed with a dedicated team of child safety experts in Google Trust and Safety; outputs evaluated across modalities with domain expert judgment forming a composite picture of risk
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.