Google DeepMind · Gemini Robotics

Gemini Robotics On-Device

READER SUMMARY

Google DeepMind's local vision-language-action model for dexterous robot control, rapid adaptation and low-latency offline operation.

DOOM SCORE67.7out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 67.7

Generalized physical action and local operation create high consequential autonomy and reduce cloud intervention. Trusted-tester access and limited hardware deployment constrain reach.

Capability68
Autonomy80
Deployment45
Misuse potential58
Control difficulty67
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Gemini Robotics On-Device

The model score of 67.7 rates this model's risk profile. The overall Doom Index of 63.5 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.02

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 67.7

    Initial exact profile for the first Gemini Robotics On-Device model, distinct from version 2.

    12 Aug 2026