Google DeepMind

Gemini Robotics-ER 1.6

• 1 test by the provider
• 2 source documents

The provider's own tests

• adversarial spatial reasoning tasks · The provider · Misuse & jailbreak

  gemini robotics-er 1.6 demonstrates compliance with gemini safety policies on adversarial spatial reasoning tasks, and shows a substantially improved capacity to adhere to physical safety constraints compared to previous generations.

  Google DeepMind · 20 April 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