> GPT-5.2 is a closed AI model from OpenAI, released 11 Dec 2025. Index score 162 (GPT-4 = 100), rank 38 of 229 ranked models. API price $1.75 in / $14 out per million tokens, 400K context.

[Models](https://themodelindex.org/models/) /[OpenAI](https://themodelindex.org/labs/openai/)

# GPT-5.2

OpenAI

Released 11 Dec 2025

Closed

Flagship

[Compare](https://themodelindex.org/compare/gpt-5-2-vs-deepseek-v3-2/) [Announcement](https://openai.com/zh-Hans-CN/index/introducing-gpt-5-2/)

162151–173

Index score

#38 of 229 models

Pro mode: 167 · $21 / $168

7/ 8

Core tests taken

5 of 6 areas · plus 19 anchor tests

Frontier

Versus the frontier at release

set or matched the record

Replaced by [GPT-5.4](https://themodelindex.org/models/gpt-5-4/)

$1.75/ $14

Price per million tokens

input / output, list price

400K

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_

Among the first models to reach this score.

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

Show 13 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

91%

Humanity's Last Exam

28%

Maths

evidence

FrontierMath T1-3

67%

Coding

evidence

SWE-bench Verified

74%

Terminal-Bench

65%

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

53%

Long tasks

evidence

METR time horizon

5.9 h

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

#38

of 219 · 162

Epoch Capabilities Index

overall capability from many benchmarks

#37

of 239 · 153.5

LMArena · Maths

maths questions in chat

#60

of 373 · 1456

LMArena · Coding

coding questions in chat

#85

of 383 · 1489

LMArena · Text

overall chat quality, judged by people

#89

of 388 · 1437

LMArena · Creative writing

creative writing

#108

of 386 · 1392

LMArena · Vision

understanding images

#50

of 149 · 1243

LMArena · WebDev

building web apps and front ends

#71

of 123 · 1416

LiveBench · Overall

overall, with fresh questions to limit contamination

#34

of 58 · 74.6

LMArena · Documents

working with long documents

#39

of 41 · 1405

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

2nd

METR time horizon

Epoch AI · independent

3rd

SWE-bench Verified

Epoch AI · independent

3rd

Terminal-Bench

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

ChatGPT

app · subscription

↗

OpenAI API

API

↗

#### API providers · 2 · per million tokens, in / out

O

OpenAI

$3.5 / $28

cheapest

A

Azure

$1.75 / $14

↗

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

11 Dec 2025

Announcement

[openai.com ↗](https://openai.com/zh-Hans-CN/index/introducing-gpt-5-2/)

Release entry

GPT-5.2

Scored as

GPT-5.2

Artificial Analysis index

–

Pro mode

index 167 · $21 / $168 per M

Output speed

–

Hugging Face

closed weights

## OpenAI releases · around this one

GPT-5.1

Closed

12 NOV 2025

index 153

GPT-5.1-Codex-Max

Closed

19 NOV 2025

index 157

GPT-5.2

Closed

11 DEC 2025

index 162

GPT-5.2-Codex

Closed

18 DEC 2025

GPT-5.3-Codex

Closed

5 FEB 2026

index 170

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