GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Quantized at FP8.
Added Dec 11, 2025
Model weightsContext Window
128.0K
Max Output
24.0K
Input Price (Auto)
$0.30/1M
Output Price (Auto)
$0.90/1M
Cache Read (Auto)
$0.15/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
11.0
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
56.6%
Better than 36% of models compared
HLE
Humanity's Last Exam
3.7%
Better than 7% of models compared
IFBench
Instruction-following benchmark
27.9%
Better than 12% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
30.7%
Better than 39% of models compared
AA-LCR
Long context reasoning evaluation
12.3%
Better than 26% of models compared
CritPt
Research-level physics reasoning
0.0%
Coding
SciCode
Python programming for scientific computing
27.2%
Better than 37% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
3.0%
Better than 23% of models compared
LiveCodeBench
Contamination-free coding benchmark
41.1%
Better than 49% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
26.3%
Better than 28% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
75.2%
Better than 50% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
17.4%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
66.6%
Last updated Jun 28, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare GLM 4.6V with similar models from the same provider or model family.
GLM 5.3 Preview
zai-org/glm-5.3A preview of GLM-5.3 for long-horizon autonomous coding and engineering workflows. This variant defaults to the model's low reasoning tier for faster responses. While in preview, prompts and responses may be logged and used for training.
GLM 5.3 Preview Thinking
zai-org/glm-5.3:thinkingThe GLM-5.3 preview with higher reasoning enabled for harder long-horizon coding, autonomous agent workflows, and complex engineering tasks. While in preview, prompts and responses may be logged and used for training.
GLM 5.2
zai-org/glm-5.2GLM-5.2 is Z.AI's flagship model for long-horizon autonomous coding and engineering workflows. It is built to plan, execute, iterate, and optimize complex development tasks over extended runs. This variant keeps thinking disabled for faster direct responses.
GLM 5.2 Thinking
zai-org/glm-5.2:thinkingGLM-5.2 with thinking enabled for harder long-horizon coding, autonomous agent workflows, complex engineering optimization, and real-world development tasks.
GLM Latest
zai-org/glm-latestCompatibility alias that routes to the newest thinking GLM model. Currently routes to GLM 5.2 Thinking.
GLM 5.1
zai-org/glm-5.1GLM-5.1 is Zhipu's next-level open source model, ranking #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo (as of April 2026). Built for long-horizon tasks, it can run autonomously for up to 8 hours. Run at FP8.