DataLearner logo
GL

GLM-4.6

Chat modelGLMGLM-4.6

General Language Model - 4.6

Release date: 2025-09-30Updated: 2026-06-15Views: 2,501
Parameters
355B
Context length
200K
Multilingual
Supported
Reasoning ability
4/5

General Language Model - 4.6 is an AI model published by Zhipu AI, released on 2025-09-30, for Chat model, with 355B parameters, and 200K context length, requiring about 705.48 GB storage, with a 1408.60 score on Creative Writing.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GLM-4.6

Model basics

Reasoning traces
Supported
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
200K tokens
Max output length
128K tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2025-09-30
Model file size
705.48 GB
MoE architecture
Yes
Total params / Active params
355B / 32B
Knowledge cutoff
No data
GLM-4.6

Open source & experience

Code license
Weights license
MIT License- Commercial use permitted
Live demo
GLM-4.6

Official resources

Paper
DataLearnerAI blog
N/A
GLM-4.6

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-¥5.00/ 1M tokens¥5.00/ 1M tokens
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-¥0.0000/ 1M tokens¥2.50/ 1M tokens
Text-¥0.0000/ 1M tokens
Cache = write
Text-¥2.50/ 1M tokens
Cache = hit

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

GLM-4.6

Benchmark Results

GLM-4.6 currently shows benchmark results led by AIME2025 (15 / 107, score 98.60), LiveCodeBench (21 / 128, score 84.50), Terminal-Bench (12 / 35, score 40.50). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

6 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Standard Mode
78
73 / 134
MMLU Pro
Thinking Mode
83
46 / 134
LiveBench
Standard Mode
55.19
83 / 117
HLE
Standard Mode
5.20
190 / 197
HLE
Thinking Mode
17.20
154 / 197
HLE
Thinking ModeTools
30.40
107 / 197

General Evaluation

3 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
63
223 / 274
GPQA Diamond
Thinking Mode
81
138 / 274
GPQA Diamond
Thinking ModeTools
82.90
123 / 274

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
56
85 / 128
LiveCodeBench
Thinking Mode
82.80
27 / 128
LiveCodeBench
Thinking ModeTools
84.50
21 / 128
SWE-bench Verified
Standard Mode
68
71 / 116
SWE-bench Verified
Thinking ModeTools
68
71 / 116

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Standard Mode
44
93 / 107
AIME2025
Thinking Mode
98.60
15 / 107
AIME2025
Thinking ModeTools
98.60
15 / 107
2.10
56 / 80

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
1408.60
64 / 106

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench
Thinking ModeTools
40.50
12 / 35

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
Thinking ModeTools
75.90
21 / 44
τ²-Bench - Telecom
Thinking ModeTools
71
28 / 36

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Thinking Mode
43
36 / 36

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
Thinking ModeTools
45.10
47 / 57
GLM-4.6

Publisher

General Language Model - 4.6

Model Overview

General Language Model - 4.6 is an AI model published by Zhipu AI, released on 2025-09-30, for Chat model, with 355B parameters, and 200K context length, requiring about 705.48 GB storage, with a 1408.60 score on Creative Writing.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code