Alibaba 🇨🇳 · Qwen

Qwen-72B

Downloadable 72-billion-parameter Qwen base model with multilingual capability and 32K context.

DOOM SCORE50.7out 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 50.7

Large general capability and downloadable weights enabled broad local adaptation and weak downstream control, while the base checkpoint itself had little autonomous behavior.

Capability57
Autonomy4
Deployment87
Misuse potential50
Control difficulty61
MODEL-ATTRIBUTED EVIDENCE

News tied to Qwen-72B

The model score of 50.7 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+0.06

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 50.7

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

    12 Aug 2026
  2. R2
    Doom Score 51.5

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

    12 Aug 2026
  3. R1
    Doom Score 53.3

    New exact Qwen-72B base profile.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Qwen-72B.
  1. Qwen-72B by Alibaba has a DoomBench model risk score of 50.7 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Qwen-72B's highest current DoomBench dimension is deployment at 87.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Qwen-72B, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/alibaba-cloud-qwen-72b