GLM-4.5-Air
Compact open-weight 106-billion-parameter mixture-of-experts tier for reasoning, coding and agentic use.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 78.8
Lower compute needs make this open tier easier to deploy broadly; capability and autonomy are below the flagship but diffusion and residual containment difficulty are higher.
News tied to GLM-4.5-Air
The model score of 78.8 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.
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.
Z.ai releases open-weight GLM-4.5 and GLM-4.5-Air agentic models
Z.ai released GLM-4.5 and GLM-4.5-Air with open weights and unified reasoning, coding and agent capabilities, including 355-billion and 106-billion-parameter mixture-of-experts variants.
- Full item contribution
- +0.20
- GLM-4.5-Air equal share
- +0.10
Model score history
-
R2
Doom Score 78.8
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 78.9
New exact July 2025 compact open model profile anchored to the company release and official repository.
12 Aug 2026