Google 🇺🇸 · Gemma 4

Gemma 4 26B MoE

Workstation-scale Apache-licensed Gemma 4 mixture-of-experts model for local reasoning, coding, and agents.

DOOM SCORE73.9out of 100model risk profile, not the overall index
0 comments · 0 votesOpen discussion

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

No comments yet. Start the discussion.

CURRENT ASSESSMENT · REVISION 3

Why this model scores 73.9

Capable workstation-scale agent support, permissive weights, and broad tooling increase diffusion and adaptation, with hardware needs limiting deployment slightly.

Capability81
Autonomy73
Deployment94
Misuse potential62
Control difficulty58
MODEL-ATTRIBUTED EVIDENCE

News tied to Gemma 4 26B MoE

The model score of 73.9 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+0.05

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.

AUDIT TRAIL

Model score history

  1. R3
    Doom Score 73.9

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

    12 Aug 2026
  2. R2
    Doom Score 74.1

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

    11 Aug 2026
  3. R1
    Doom Score 73.9

    New exact tier verified from dated primary launch.

    11 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Gemma 4 26B MoE.
  1. Gemma 4 26B MoE by Google has a DoomBench model risk score of 73.9 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Gemma 4 26B MoE's highest current DoomBench dimension is deployment at 94.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Gemma 4 26B MoE, 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-gemma-4-26b-moe