Alibaba 🇨🇳 · Qwen2.5

Qwen2.5-72B-Instruct

Alibaba's flagship open-weight Qwen2.5 instruction model with 72 billion parameters, 128K context, structured output, multilingual reasoning, coding, mathematics, and tool-calling support.

DOOM SCORE64.2out 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 64.2

Strong general capability and downloadable weights create broad deployment and misuse exposure with limited downstream provider control, while inherent autonomy remains modest without an external agent scaffold.

Capability72
Autonomy18
Deployment94
Misuse potential68
Control difficulty73
MODEL-ATTRIBUTED EVIDENCE

News tied to Qwen2.5-72B-Instruct

The model score of 64.2 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+0.19

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.

Capability TOWARD

Alibaba releases the open Qwen2.5 model family

Alibaba released Qwen2.5 language, coding, and mathematics models across sizes from 0.5 billion to 72 billion parameters, with long context, structured outputs, tool calling, and mostly Apache-2.0 weights.

Full item contribution
+0.19
Qwen2.5-72B-Instruct equal share
+0.19
Read assessment →
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 64.2

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

    12 Aug 2026
  2. R2
    Doom Score 65.2

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

    12 Aug 2026
  3. R1
    Doom Score 67.5

    New exact open Qwen2.5 flagship instruction checkpoint verified by the dated primary release.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Qwen2.5-72B-Instruct.
  1. Qwen2.5-72B-Instruct by Alibaba has a DoomBench model risk score of 64.2 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Qwen2.5-72B-Instruct'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 Qwen2.5-72B-Instruct, 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-qwen2-5-72b-instruct