Language modelActive

GLM-4.6V

Z.ai

Released: December 7, 2025
Data date: September 8, 2026
Predecessor: GLM-4.5V

Speed: 42 tokens/s
Output throughput
Price: $0.3 · $0.9
Input · Output / 1M tokens
Input: Text, Image, Video
Output: Text

GLM-4.6V introduces native multimodal function calling in Z.ai’s GLM line. The MoE checkpoint handles text, images, and video with 106B total parameters, 12B active parameters, and a 131,072-token context. Visual input can therefore enter a tool workflow directly.

Output remains text, while reasoning and direct responses are documented as separate modes. GLM-4.5V is the earlier vision entry in the same line. GLM-4.6V mainly extends it with the larger context and native multimodal tool calls.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	106BSource
Active parameters	12BSource
Context window	131,072 tokensSource
License	MITSource
Architecture	vision-language MoE with native multimodal function callingSource
Parameters	106 BSource
Active parameters	12 BSource
Rounded context label	128kSource
Model configuration context	131,072 tokens (Native checkpoint context; distinct from the rounded model-card label.)Source
Input	Text, Image, VideoSource
Output	TextSource
Reasoning mode	thinking, non-thinkingSource
Tool calling	YesSource
Maximum output	16,384 tokensSource
Decoding	top_p 0.6, top_k 2, temperature 0.8, repetition_penalty 1.1Source

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

MMBench V1.1 (Show measurement, test conditions, and source)

Source value: 88.8
Score: 88.8
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

MMBench V1.1 CN (Show measurement, test conditions, and source)

Source value: 88.2
Score: 88.2
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

MMStar (Show measurement, test conditions, and source)

Source value: 75.9
Score: 75.9
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

BLINK Val (Show measurement, test conditions, and source)

Source value: 65.5
Score: 65.5
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

MUIRBench (Show measurement, test conditions, and source)

Source value: 77.1
Score: 77.1
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

MMMU Val (Show measurement, test conditions, and source)

Source value: 76
Score: 76
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

MMMU Pro (Show measurement, test conditions, and source)

Source value: 66
Score: 66
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

VideoMMMU (Show measurement, test conditions, and source)

Source value: 74.7
Score: 74.7
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

MathVista (Show measurement, test conditions, and source)

Source value: 85.2
Score: 85.2
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

AI2D (Show measurement, test conditions, and source)

Source value: 88.8
Score: 88.8
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

DynaMath (Show measurement, test conditions, and source)

Source value: 54.5
Score: 54.5
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

WeMath (Show measurement, test conditions, and source)

Source value: 69.8
Score: 69.8
Metric: percent
Unit: %
Category: multimodal
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.6V benchmark image
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GLM-4.6V column; image labels model scales and comparator settings

Source GLM-4.6V benchmark image

Page 1 of 4

Predecessor and successor

Sources and data date

Type	Evidence and data date
Speed	Median across serving providers, Non-reasoning. Output speed after the first streaming chunk, not total response time. Classified as deprecated by Artificial Analysis. Artificial Analysis maintains only the default 10K-input workload there. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · GLM-4.6V documentation · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · GLM-4.6V documentation · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 5 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Unresolved	release-date Original wording No normalized release-date field.
Additional source	Model metadata · GLM-4.6V model card · Editorial description reviewed October 2, 2026
Additional source	GLM-4.6V benchmark image (retrieved September 8, 2026)
Additional source	Model metadata (retrieved September 8, 2026) · GLM-4.6V configuration · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0
Additional source	Z.ai Developer Docs, release notes index (2026-09-19)

GLM-4.6V

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Popularity

Published prices

Predecessor and successor

Sources and data date