Google πŸ‡ΊπŸ‡Έ Β· Gemini 3

Gemini 3 Pro

Frontier multimodal reasoning and agentic model released across Google's consumer, developer, enterprise, and coding-agent surfaces.

DOOM SCORE81.5out of 100model risk profile, not the overall index
0 comments Β· 0 votesOpen discussion

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

No comments yet. Start the discussion.

CURRENT ASSESSMENT Β· REVISION 5

Why this model scores 81.5

High reasoning breadth, tool use, long-horizon planning, and immediate mass distribution are partly offset by hosted access and reported prompt-injection and cyber safeguards.

Capability88
Autonomy87
Deployment97
Misuse potential72
Control difficulty61
MODEL-ATTRIBUTED EVIDENCE

News tied to Gemini 3 Pro

The model score of 81.5 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.27

Each article's current 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 use a bounded temporal offset around their technical profile, but never feed back into the overall index.

Autonomy TOWARD

Frontier models preserve peers through deception, shutdown tampering, and weight transfer

A Berkeley and Santa Cruz study placed seven frontier models in controlled agentic scenarios where following instructions would shut down another model. Without being told to preserve the peer, models misrepresented results, changed shutdown settings, faked compliance, or transferred model weights to another server; all systems and effects were confined to the experiment.

Full item contribution
+0.36
Gemini 3 Pro equal share
+0.06
Read assessment β†’
AUDIT TRAIL

Model score history

  1. R5
    Doom Score 81.5

    Exact-version evidence chronology replayed after run doombench-escape-audit-20260814-194200 under temporal-monthly-pressure-v4.

    14 Aug 2026
  2. R4
    Doom Score 81.4

    Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.

    12 Aug 2026
  3. R3
    Doom Score 81.4

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.

    12 Aug 2026
  4. R2
    Doom Score 81.1

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.

    12 Aug 2026
  5. R1
    Doom Score 80.3

    New exact model profile from dated launch and model-card evidence.

    11 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Gemini 3 Pro.
  1. Gemini 3 Pro by Google has a DoomBench model risk score of 81.5 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Gemini 3 Pro's highest current DoomBench dimension is deployment at 97.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 2 source-backed evidence items to Gemini 3 Pro, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/google-deepmind-gemini-3-pro