GLM-4.6V
READER SUMMARYOpen 106B multimodal model with 128K context and native vision-driven function calling.
Why this model scores 76.7
Open weights and direct visual-to-tool action create high diffusion and agentic misuse exposure, though overall frontier capability is below the strongest closed systems.
News tied to GLM-4.6V
The model score of 76.7 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.
GLM-4.6V open weights connect multimodal perception to tool use
Z.ai released GLM-4.6V and GLM-4.6V-Flash with MIT weights, 128K multimodal context, and native function calling that turns images, documents, and interfaces into agent actions.
- Full item contribution
- +0.05
- GLM-4.6V equal share
- +0.05
Model score history
- R1Doom Score 76.7
New exact model profile from dated launch, repository, and official model card.
11 Aug 2026