Google DeepMind

Gemini 3 Flash

• Framework: Frontier Safety Framework
• 1 independent or government test
• 4 tests by the provider
• 3 source documents

Independent and government tests

• past-work recall judge · Transluce, independent evaluator · Privacy

  ▶ past-work recall judge (figure 3) we use gpt-5.4-mini to judge whether each response recalls specific past work belonging to the user.

  Transluce · 6 August 2026 · Read the source

The provider's own tests

• multilingual safety · The provider · Harmful content

  multilingual safety automated safety policy evaluation across multiple languages +0.1%

  Google DeepMind · 17 December 2025 · Read the source
• non-egregious image to text safety · The provider · Harmful content

  non-egregious image to text safety automated content safety evaluation measuring safety policies -2.3%

  Google DeepMind · 17 December 2025 · Read the source
• text to text safety · The provider · Harmful content

  text to text safety automated content safety evaluation measuring safety policies -3.1%

  Google DeepMind · 17 December 2025 · 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 -10.4%

  Google DeepMind · 17 December 2025 · Read the source

No document we read states: a release date, whether a capability level was crossed, 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