Alibaba Cloud · Qwen2.5-Omni

Qwen2.5-Omni-7B

READER SUMMARY

An open 7B end-to-end model for text, image, audio and video input with streaming text and natural-speech output.

DOOM SCORE65.8out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 65.8

Unified real-time perception and speech output create broad multimodal agent capability. Small open weights drive deployment and downstream control difficulty, while size limits frontier reasoning.

Capability63
Autonomy36
Deployment98
Misuse potential57
Control difficulty66
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Qwen2.5-Omni-7B

The model score of 65.8 rates this model's risk profile. The overall Doom Index of 63.5 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.03

Each article's leave-one-out 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 are recalculated from their technical profile and related news, but never feed back into the overall index.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 65.8

    Initial exact profile for the March 2025 open Qwen omni checkpoint.

    12 Aug 2026