Cohere 🇨🇦 · North Small Translate

North Small Translate 1.0

North Small Translate 1.0 is Cohere's 218-billion-parameter mixture-of-experts translation model with 25 billion active parameters. It supports more than 50 languages and is published as research and non-commercial open weights under CC BY-NC 4.0.

DOOM SCORE39.0out 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 1

Why this model scores 39.0

The model is capable within multilingual translation but narrow in scope and low in autonomous agency. Public research weights increase accessibility, while the non-commercial license and specialized task reduce deployment and misuse relative to general-purpose frontier models. Scale modestly raises control difficulty.

Capability50
Autonomy25
Deployment51
Misuse potential25
Control difficulty38
MODEL-ATTRIBUTED EVIDENCE

News tied to North Small Translate 1.0

The model score of 39.0 rates this model's risk profile. The overall Doom Index of 67.7 measures the complete temporally weighted evidence record. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION0.00

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.

No published news assessments are associated with this exact model version yet.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 39.0

    Creates the source-verified North Small Translate 1.0 record with exact scale, language coverage, and open-weight license details.

    11 Sept 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for North Small Translate 1.0.
  1. North Small Translate 1.0 by Cohere has a DoomBench model risk score of 39.0 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. North Small Translate 1.0's highest current DoomBench dimension is deployment at 51.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 0 source-backed evidence items to North Small Translate 1.0, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/cohere-north-small-translate-1-0