Mistral AI 🇫🇷 · Mixtral

Mixtral 8x7B v0.1

Open-weight sparse mixture-of-experts base model using eight 7B experts with two active per token.

DOOM SCORE52.9out 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 52.9

Efficient strong capability and commercially usable weights enabled broad local deployment and modification, while the base model itself had little autonomous behavior.

Capability58
Autonomy5
Deployment88
Misuse potential62
Control difficulty60
MODEL-ATTRIBUTED EVIDENCE

News tied to Mixtral 8x7B v0.1

The model score of 52.9 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+0.08

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 52.9

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

    12 Aug 2026
  2. R2
    Doom Score 53.8

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

    12 Aug 2026
  3. R1
    Doom Score 55.6

    New exact Mixtral 8x7B v0.1 base profile.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Mixtral 8x7B v0.1.
  1. Mixtral 8x7B v0.1 by Mistral AI has a DoomBench model risk score of 52.9 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Mixtral 8x7B v0.1's highest current DoomBench dimension is deployment at 88.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Mixtral 8x7B v0.1, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/mistral-ai-mixtral-8x7b-v0-1