Frontier Log

GoogleMinor

Google launches Gemini Robotics 2.5

Google DeepMind's most capable vision-language-action model to date, rolling out to robotics partners.

Today, we are introducing Gemini Robotics 2.5, our most capable vision-language-action (VLA) model to date.

From the announcement

Official source

Gemini Robotics 2.5: Accelerating Physical Intelligencedeepmind.google · published

Model

Gemini Robotics 2.5

Google · Announced

Benchmark scores not yet recorded

Related

Tags

See it on the timeline