GL

GLM-4.7

Chat modelGLMGLM-4.7

GLM-4.7

Release date: 2025-12-22Updated: 2026-06-15 07:18:19.2523,850
Parameters
358B
Context length
200K
Chinese support
Supported
Reasoning ability

GLM-4.7 is an AI model published by 智谱AI, released on 2025-12-22, for Chat model, with 358B parameters, and 200K context length, under the MIT License license, with a 95.70 score on AIME2025.

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

GLM-4.7

Model basics

Reasoning traces
Supported
Thinking modes
Standard ModeThinking Level · Extended
Context length
200K tokens
Max output length
132072 tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2025-12-22
Model file size
No data
MoE architecture
Yes
Total params / Active params
358B / 32B
Knowledge cutoff
No data
GLM-4.7

Open source & experience

Code license
Weights license
MIT License- 免费商用授权
GLM-4.7

Official resources

DataLearnerAI blog
No blog post yet
GLM-4.7

API details

API speed
3/5
No public API pricing yet.
GLM-4.7

Benchmark Results

GLM-4.7 currently shows benchmark results led by LiveCodeBench (17 / 120, score 84.90), τ²-Bench (6 / 40, score 87.40), AIME2025 (23 / 106, score 95.70). 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

5 evaluations
Benchmark / mode
Score
Rank/total
85.70
45 / 179
84.30
36 / 126
LiveBench
Standard Mode
58.09
78 / 115
42.80
42 / 159
24.80
90 / 159

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
84.90
17 / 120
73.80
39 / 108

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
95.70
23 / 106
92.90
7 / 15
2.10
56 / 80

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Thinking Mode
47.70
29 / 63

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
87.40
6 / 40

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
52
34 / 45

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
MCP-Atlas
Standard ModeTools
58.10
18 / 23

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

GLM-4.7

Publisher

GLM-4.7

Model Overview

GLM-4.7 is an AI model published by 智谱AI, released on 2025-12-22, for Chat model, with 358B parameters, and 200K context length, under the MIT License license, with a 95.70 score on AIME2025.

DataLearner on WeChat

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

DataLearner WeChat QR code