> GLM-4.7 is an open-weights AI model from Zhipu, released 22 Dec 2025. Index score 139 (GPT-4 = 100), rank 91 of 229 ranked models. API price $0.60 in / $2.2 out per million tokens, 205K context.

[Models](https://themodelindex.org/models/) /[Zhipu](https://themodelindex.org/labs/zhipu/)

# GLM-4.7

Zhipu

Released 22 Dec 2025

Open

Date verified

[Compare](https://themodelindex.org/compare/glm-4-7-vs-gpt-5-2/) [Announcement](https://huggingface.co/zai-org/GLM-4.7)

139127–150

Index score

#91 of 229 models

2/ 8

Core tests taken

2 of 6 areas · plus 9 anchor tests

−23

Versus the frontier at release

best then: GPT-5.2

Replaced by [GLM-5](https://themodelindex.org/models/glm-5/)

$0.60/ $2.2

Price per million tokens

input / output, list price

205K

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

Gemini 2.5 Pro reached this score 9 months earlier.

## Test results · by area · tick = best by any model

Show 7 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

83%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

33%

Agents

no evidence yet

APEX-Agents

no result

Novel problems

no evidence yet

ARC-AGI-2

no result

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#91

of 219 · 139

LMArena · Text

overall chat quality, judged by people

#83

of 388 · 1442

LMArena · Creative writing

creative writing

#89

of 386 · 1405

LMArena · Coding

coding questions in chat

#91

of 383 · 1484

LMArena · Maths

maths questions in chat

#99

of 373 · 1428

Epoch Capabilities Index

overall capability from many benchmarks

#88

of 239 · 143.5

LMArena · WebDev

building web apps and front ends

#67

of 123 · 1435

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Replaced by GLM-5; it no longer leads any category among current models.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

Z.ai Chat

app · subscription

↗

Z.ai API

API

↗

#### API providers · 7 · per million tokens, in / out

D

DeepInfra

$0.40 / $1.75 · fp4

cheapest

V

Venice

$0.40 / $1.93 · fp4

↗

A

AtlasCloud

$0.52 / $1.85 · fp8

↗

N

Novita

$0.54 / $1.98 · fp8

↗

G

Google

$0.60 / $2.2

↗

Z

Z.AI

$0.60 / $2.2 · fp4

↗

M

Mancer 2

$0.70 / $2.5 · fp4

↗

#### Run it yourself

🤗

Official weights

zai-org/GLM-4.7

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

22 Dec 2025

Announcement

[huggingface.co ↗](https://huggingface.co/zai-org/GLM-4.7)

Release entry

GLM-4.7

Scored as

GLM-4.7

Artificial Analysis index

–

Output speed

–

Hugging Face

[zai-org/GLM-4.7 ↗](https://huggingface.co/zai-org/GLM-4.7)

## Zhipu releases · around this one

GLM-4.5

Open

28 JUL 2025

GLM-4.6

Open

30 SEP 2025

GLM-4.7

Open

22 DEC 2025

index 139

GLM-5

Open

11 FEB 2026

index 144

GLM-5.1

Open

7 APR 2026

index 153

---
Source: https://themodelindex.org/models/glm-4-7/ · The Model Index · data as of 2026-10-01