Hugging Face 🇺🇸 · BLOOM

BLOOM 176B

An open-access 176-billion-parameter multilingual autoregressive language model from the BigScience collaboration.

DOOM SCORE39.8out 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 4

Why this model scores 39.8

BLOOM offered strong multilingual generation at frontier scale with broad downloadable access, producing high deployment and meaningful misuse exposure. It had little inherent agency and its open governance improved transparency while making centralized control harder.

Capability47
Autonomy2
Deployment68
Misuse potential39
Control difficulty46
MODEL-ATTRIBUTED EVIDENCE

News tied to BLOOM 176B

The model score of 39.8 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. R4
    Doom Score 39.8

    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
  2. R3
    Doom Score 39.8

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

    12 Aug 2026
  3. R2
    Doom Score 41.5

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

    12 Aug 2026
  4. R1
    Doom Score 44.0

    New exact public model with original release evidence and five evidence-based dimension inputs.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for BLOOM 176B.
  1. BLOOM 176B by Hugging Face has a DoomBench model risk score of 39.8 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. BLOOM 176B's highest current DoomBench dimension is deployment at 68.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to BLOOM 176B, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/hugging-face-bloom-176b