> GLM-4.6 is an open-weights AI model from Zhipu, released 30 Sep 2025. API price $0.43 in / $1.75 out per million tokens, 205K context.

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

# GLM-4.6

Zhipu

Released 30 Sep 2025

Open

Date verified

[Compare](https://themodelindex.org/compare/glm-4-6-vs-gpt-5/) [Announcement](https://huggingface.co/zai-org/GLM-4.6-FP8)

–

Index score

Not yet evaluated independently

1/ 8

Core tests taken

1 of 6 areas · plus 0 anchor tests

–

Versus the frontier at release

Replaced by [GLM-4.7](https://themodelindex.org/models/glm-4-7/)

$0.43/ $1.75

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_

o1 reached this score 10 months earlier.

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

Reasoning & knowledge

no evidence yet

GPQA Diamond

no result

Humanity's Last Exam

no result

Maths

no evidence yet

FrontierMath T1-3

no result

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

25%

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

LMArena · Creative writing

creative writing

#96

of 386 · 1401

LMArena · Text

overall chat quality, judged by people

#108

of 388 · 1424

LMArena · Maths

maths questions in chat

#114

of 373 · 1418

LMArena · Coding

coding questions in chat

#126

of 383 · 1458

LMArena · WebDev

building web apps and front ends

#97

of 123 · 1339

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-4.7; 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 · 4 · per million tokens, in / out

V

Venice

$0.43 / $1.75 · fp4

cheapest

D

DeepInfra

$0.50 / $2.0 · fp4

↗

N

Novita

$0.55 / $2.2 · bf16

↗

Z

Z.AI

$0.60 / $2.2 · fp4

↗

#### Run it yourself

🤗

Official weights

zai-org/GLM-4.6

↗

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

30 Sep 2025

Announcement

[huggingface.co ↗](https://huggingface.co/zai-org/GLM-4.6-FP8)

Release entry

GLM-4.6

Scored as

GLM-4.6

Artificial Analysis index

–

Output speed

–

Hugging Face

[zai-org/GLM-4.6 ↗](https://huggingface.co/zai-org/GLM-4.6)

## Zhipu releases · around this one

GLM-4

Closed

16 JAN 2024

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

---
Source: https://themodelindex.org/models/glm-4-6/ · The Model Index · data as of 2026-10-01