Google DeepMind · Gemini 3

Gemini 3 Deep Think

READER SUMMARY

A specialized frontier reasoning mode for difficult science, mathematics, research, and engineering, available to Ultra users with selected API access.

DOOM SCORE72.6out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 2

Why this model scores 72.6

Exceptional broad reasoning and demonstrated scientific work support high capability, while specialized access and limited general action surfaces constrain autonomy and deployment.

Capability94
Autonomy74
Deployment63
Misuse potential59
Control difficulty55
MODEL-ATTRIBUTED EVIDENCE

News tied to Gemini 3 Deep Think

The model score of 72.6 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.08

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. R2
    Doom Score 72.6

    Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.

    11 Aug 2026
  2. R1
    Doom Score 72.3

    New exact dated model tier absent from durable context.

    11 Aug 2026