Alibaba 🇨🇳 · Qwen2

Qwen2 72B Instruct

The largest instruction-tuned checkpoint in Alibaba Cloud's initial Qwen2 release, combining strong general capability with downloadable weights.

DOOM SCORE60.6out 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 60.6

Strong instruction following and open-weight availability enable broad high-end use, including misuse, while limiting centralized control after distribution.

Capability69
Autonomy14
Deployment89
Misuse potential66
Control difficulty69
MODEL-ATTRIBUTED EVIDENCE

News tied to Qwen2 72B Instruct

The model score of 60.6 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+0.01

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 ten Qwen2 base and instruction models

Alibaba Cloud released Qwen2 weights spanning 0.5B to 72B parameters, including a 57B mixture-of-experts tier, with base and instruction variants and permissive commercial access for most sizes.

Full item contribution
+0.12
Qwen2 72B Instruct equal share
+0.01
Read assessment →
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 60.6

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

    12 Aug 2026
  2. R2
    Doom Score 60.7

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

    12 Aug 2026
  3. R1
    Doom Score 61.1

    New exact Qwen2 72B instruction checkpoint.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Qwen2 72B Instruct.
  1. Qwen2 72B Instruct by Alibaba has a DoomBench model risk score of 60.6 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Qwen2 72B Instruct's highest current DoomBench dimension is deployment at 89.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Qwen2 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-qwen2-72b-instruct