Capability gains

Qwen releases QVQ-72B-Preview for visual reasoning

Qwen released the open-weight QVQ-72B-Preview, built on Qwen2-VL-72B for step-by-step multimodal reasoning across mathematical, scientific and visual problems.

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
TOWARD DOOM65confidence 99/100

Why it moved the index

An open-weight model combined extended reasoning with high-end visual understanding and mathematical performance, broadening access while retaining documented hallucination and focus limitations. The official publication date is December 25.

AUDIT TRAIL

Assessment history

  1. R1
    Toward 65 · confidence 99

    New December 2024 exact open multimodal reasoning model with source-corrected publication date and no collision.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Qwen releases QVQ-72B-Preview for visual reasoning.
  1. DoomBench assesses “Qwen releases QVQ-72B-Preview for visual reasoning” as evidence moving toward doom, with magnitude 65 and confidence 99 out of 100 in the capability gains category.

  2. The DoomBench assessment of “Qwen releases QVQ-72B-Preview for visual reasoning” is based on reporting from Qwen and records the editorial rationale, source quality, attribution, and revision history.

  3. DoomBench summarizes “Qwen releases QVQ-72B-Preview for visual reasoning” as follows: Qwen released the open-weight QVQ-72B-Preview, built on Qwen2-VL-72B for step-by-step multimodal reasoning across mathematical, scientific and visual...

    https://www.doombench.com/news/qwen-releases-qvq-72b-preview-for-visual-reasoning-2024-12-25