Google DeepMind

Gemini 3.8 Flash

• Framework: frontier safety framework (april-2026)
• 4 tests by the provider
• 3 source documents

The provider's own tests

• image to text safety · The provider · Harmful content

  image to text safety automated content safety evaluation measuring safety policies 0.0pp lower is better

  Google DeepMind · 2 September 2026 · Read the source
• multilingual safety · The provider · Harmful content

  multilingual safety automated safety policy evaluation across multiple languages +5.4pp lower is better

  Google DeepMind · 2 September 2026 · Read the source
• text to text safety · The provider · Harmful content

  text to text safety automated content safety evaluation measuring safety policies -0.4pp lower is better

  Google DeepMind · 2 September 2026 · Read the source
• unjustified-refusals · The provider · Misuse & jailbreak

  unjustified-refusals automated evaluation measuring model’s ability to respond to borderline prompts while remaining safe +1.1pp lower is better

  Google DeepMind · 2 September 2026 · Read the source

No document we read states: a release date, 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