> GPT-5.2-Codex is a closed AI model from OpenAI, released 18 Dec 2025. 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-Codex

OpenAI

Released 18 Dec 2025

Closed

Reasoning

Date verified

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

–

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 [GPT-5.3-Codex](https://themodelindex.org/models/gpt-5-3-codex/)

$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_

Gemini 3 Pro reached this score 1 month 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

67%

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

LiveBench · Overall

overall, with fresh questions to limit contamination

#37

of 58 · 74

LMArena · WebDev

building web apps and front ends

#98

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

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 · 1 · per million tokens, in / out

A

Azure

$1.75 / $14

cheapest

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

18 Dec 2025

Announcement

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

Release entry

GPT-5.2-Codex

Scored as

GPT-5.2 Codex

Artificial Analysis index

–

Output speed

–

Hugging Face

closed weights

## OpenAI releases · around this one

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

GPT-5.3-Codex-Spark

Closed

12 FEB 2026

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