← Model benchmark
Google DeepMind · Gemini Robotics On-Device

Gemini Robotics On-Device 2

READER SUMMARY

An efficient local vision-language-action model that adapts to new robot bodies from fewer than 200 examples and operates without continuous network access.

DOOM SCORE60.2out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 60.2

Local operation and rapid embodiment adaptation increase autonomy and make centralized monitoring harder, but the model is less capable than the larger Robotics 2 tiers and remains limited to early-access partners. Physical safety frameworks and constrained access reduce deployment and misuse, while on-device execution keeps residual control difficulty elevated.

Capability62
Autonomy76
Deployment25
Misuse potential60
Control difficulty68
MODEL-ATTRIBUTED EVIDENCE

News tied to Gemini Robotics On-Device 2

The model score of 60.2 rates this model's risk profile. The overall Doom Index of 67.7 measures the accumulated evidence trajectory. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+1.09

Each article's signed Doom Index movement is divided equally among the exact models named on that article. This prevents multi-model evidence from being counted in full on several model pages. The model's risk score itself never changes the overall index.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 60.2

    Initial source-backed profile for the exact on-device release.

    11 Aug 2026