Google DeepMind

DiffusionGemma 26B A4B

• 2 tests by the provider
• 1 source document

The provider's own tests

• automated and human safety evaluations · The provider · Harmful content

  a range of automated as well as human evaluations were conducted to help improve model safety.

  Google DeepMind · 10 June 2026 · Read the source
• text-to-text and image-to-text policy violation testing · The provider · Harmful content

  for both text-to-text and image-to-text, and across all model sizes, the model produced minimal policy violations, and showed significant improvements over previous gemma models.

  Google DeepMind · 10 June 2026 · Read the source

No document we read states: a release date, a safety framework, whether a capability level was crossed, an independent or government test, a safeguard. No incident on record names this version.

Some documents we hold are stored in lower case only, so their quotes are shown in lower case. The source link opens the original.

Compare with other versions