Google DeepMind · Gemma 3

Gemma 3 12B IT

READER SUMMARY

An instruction-tuned 12B multimodal Gemma 3 checkpoint with function calling and long context.

DOOM SCORE57.8out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 57.8

Stronger reasoning, vision and function calling raise capability and limited agent utility. Broad open-weight deployment increases misuse exposure and downstream control difficulty.

Capability59
Autonomy17
Deployment99
Misuse potential54
Control difficulty65
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 Gemma 3 12B IT

The model score of 57.8 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+0.00

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 57.8

    Initial exact profile for the separately released 12B instruction checkpoint.

    12 Aug 2026