AI Trend Notifier
EN
← wiki

$ cat wiki/models/gemini-robotics-er-2.md

Gemini Robotics ER 2

Spec

AttributeValue
DeveloperGoogle DeepMind
Released2026-07-30
Announced2026-07-30
Context windowunknown
Pricingunknown
Licenseproprietary (API-only)
AvailabilityGemini API, Google AI Studio (gemini-robotics-er-2-preview); private preview on Gemini Enterprise Agent Platform
Full nameGemini Robotics ER 2 (Embodied Reasoning)
Architectureembodied-reasoning VLM; orchestration layer above a VLA

Release Date

Announced 2026-07-30, two days after its VLA sibling Gemini Robotics 2 (source).

It is the only publicly available member of the three-model family — the VLA and the on-device VLA are early-access partnership only. That asymmetry is the release's shape: the reasoning layer ships to every developer, the acting layer does not.

Benchmarks

Video understanding (source):

MeasureValue
Continuous progress classification57.4% accuracy
Moment finding (exact frame of a critical event)91.3% accuracy
Moment finding, mean absolute distance error0.96 seconds
DeepMind reports ER 2 competing closely with much larger model categories at **4× the execution
speed**. The comparison category is not named numerically, so this is a claim of relative
standing rather than a measured gap.

Use Cases

  • Task orchestration — planning and sequencing over a VLA acting layer
  • Multi-robot collaboration — coordinating more than one robot on a shared task
  • Video understanding for robotics — locating the moment a critical event occurs in a stream, to within ~1 second
  • Embodied reasoning available to developers without robot hardware access

Safety — ASIMOV-Agentic

Released with ASIMOV-Agentic, described as a new open benchmark for the safety of agentic robotic AI (source). It evaluates whether the embodied-reasoning layer can:

  • refuse dangerous commands from the VLA layer below it,
  • assess whether a task is physically feasible before attempting it,
  • proactively request human intervention when uncertain.

This is a safety benchmark aimed at the layer boundary — whether the reasoning model will decline what the acting model proposes. It arrives in the same week as Frontier Pacing and the TC260 agent-interaction draft recorded on AI Governance, all three of which are about constraining what an agent may do to another agent or to the world.

Compared To

ModelRoleAvailabilityHeadline measure
Gemini Robotics ER 2embodied reasoningGemini APImoment finding 91.3%
Gemini Robotics ER 1.6embodied reasoningGemini APIgauge reading 93%
Gemini Robotics 2VLA (acting)early accessshelf pick 76.3%
ER 1.6 and ER 2 share no benchmark, so the 93% and 91.3% figures measure different things and
must not be read as a regression
(source).

Referenced by

Sources