GLM-4.7
READER SUMMARYAn open-weight reasoning and coding model with tool use, long-horizon agent support, API access, and local deployment.
Why this model scores 76.6
Coding, reasoning, tool use, and persistent thinking support strong capability and autonomy; open weights and worldwide hosted and local access drive deployment and limit withdrawal.
News tied to GLM-4.7
The model score of 76.6 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.
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.
Z.ai releases open-weight GLM-4.7 for long-horizon coding agents
Z.ai released GLM-4.7 through APIs, agent tools, and downloadable weights with interleaved reasoning, tool use, and support for long-horizon coding work.
- Full item contribution
- +0.07
- GLM-4.7 equal share
- +0.07
Model score history
- R2Doom Score 76.6
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 - R1Doom Score 77.7
New source-verified open model absent from durable context.
11 Aug 2026