> GLM-5.2 is an open-weights AI model from Zhipu, released 16 Jun 2026. Index score 158 (GPT-4 = 100), rank 44 of 229 ranked models. API price $1.4 in / $4.4 out per million tokens, 1.05M context.

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

# GLM-5.2

Zhipu

Released 16 Jun 2026

Open

Date verified

[Compare](https://themodelindex.org/compare/glm-5-2-vs-claude-fable-5/) [Run it yourself →](https://themodelindex.org/local/) [Announcement](https://z.ai/blog/glm-5.2)

158147–169

Index score

#44 of 229 models

4/ 8

Core tests taken

4 of 6 areas · plus 16 anchor tests

−27

Versus the frontier at release

best then: Claude Fable 5

Replaced by [GLM-5.3](https://themodelindex.org/models/glm-5-3/)

$1.4/ $4.4

Price per million tokens

input / output, list price

1.05M

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 3 Pro reached this score 7 months earlier.

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

Show 13 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

92%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

59%

Coding

evidence

SWE-bench Verified

79%

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

23%

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

#44

of 219 · 158

LMArena · Maths

maths questions in chat

#27

of 373 · 1487

LMArena · Creative writing

creative writing

#28

of 386 · 1455

LMArena · Text

overall chat quality, judged by people

#29

of 388 · 1475

LMArena · Coding

coding questions in chat

#50

of 383 · 1512

Epoch Capabilities Index

overall capability from many benchmarks

#44

of 239 · 151.8

LMArena · WebDev

building web apps and front ends

#23

of 123 · 1605

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

1st

SWE-bench Verified

Epoch AI · independent

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 · 26 · per million tokens, in / out

B

Baidu

$0.24 / $0.85 · fp4

cheapest

S

StreamLake

$0.56 / $1.76 · fp8

↗

D

DeepInfra

$0.56 / $1.8 · fp4

↗

R

Reka

$0.70 / $1.4

↗

M

Morph

$0.28 / $2.69 · fp8

↗

D

Decart

$2.25 / $8.0 · fp4

↗

N

Novita

$0.65 / $2.04 · fp8

↗

D

DigitalOcean

$0.70 / $2.2

↗

#### Run it yourself

🤗

Official weights

zai-org/GLM-5.2

↗

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

16 Jun 2026

Announcement

[z.ai ↗](https://z.ai/blog/glm-5.2)

Release entry

GLM-5.2

Scored as

GLM-5.2

Artificial Analysis index

–

Output speed

–

Hugging Face

[zai-org/GLM-5.2 ↗](https://huggingface.co/zai-org/GLM-5.2)

## Zhipu releases · around this one

GLM-5

Open

11 FEB 2026

index 144

GLM-5.1

Open

7 APR 2026

index 153

GLM-5.2

Open

16 JUN 2026

index 158

GLM-5.3

Open

14 AUG 2026

index 167

GLM-5.3-Flash

Open

20 AUG 2026

index 158

---
Source: https://themodelindex.org/models/glm-5-2/ · The Model Index · data as of 2026-10-01