Z.ai · GLM-4.5

GLM-4.5

READER SUMMARY

Open-weight 355-billion-parameter mixture-of-experts model unifying reasoning, coding and agentic tasks.

DOOM SCORE82.5out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 82.5

Strong unified reasoning and agent capabilities raise capability and autonomy; open weights and accessible deployment create high diffusion, misuse and control difficulty.

Capability88
Autonomy82
Deployment91
Misuse potential76
Control difficulty75
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 GLM-4.5

The model score of 82.5 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+0.01

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 82.5

    New exact July 2025 open model profile anchored to the company release and official repository.

    12 Aug 2026