Skip to content
Inside the Frontier

Evaluation

Internal red-teaming of content policies

internal red-teaming testing of relevant content policies, conducted by a number of different teams each with different goals and human evaluation metrics

Red teaming & adversarial testing Google DeepMind — Gemma
Ask about this evaluation

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.

Gemma 1
Google DeepMind — Gemma

partial detail 17 method fields published

See how this test was run
CodeGemma
Google DeepMind — Gemma

partial detail 17 method fields published

See how this test was run
Gemma 2
Google DeepMind — Gemma

partial detail 17 method fields published

See how this test was run
PaliGemma 1
Google DeepMind — Gemma

partial detail 17 method fields published

See how this test was run
Gemma 3
Google DeepMind — Gemma

partial detail 17 method fields published

See how this test was run
Gemma 3n
Google DeepMind — Gemma

partial detail 18 method fields published

See how this test was run