modelgrep
O

OpenAI: GPT-5.2-Codex

openai/gpt-5.2-codex

17th smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
49.0
17th of 178
Design Elo
1188
godotgamedev
Speed
63
130th fastest
Latency
1.5s
first token
Input price
$1.75
236th cheapest
Context
400K
128K max out

How it compares

Smarter than90%
of all ranked models
Faster than56%
of all ranked models
Cheaper than21%
of all ranked models

Overview

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Benchmarks

independent · via OpenRouter
Artificial Analysis89th percentile
Intelligence Index
49.0
Coding Index
43.0
Agentic Index
56.5
GPQA Diamond
90%
Humanity's Last Exam
34%
SciCode
55%
Tau²-Bench (agentic)
92%
Design Arena · Elo6,479 tournaments
godotgamedev
1188
mobileapps
1181
androidnative
1176
webapps
1141
fullstack
1071

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
OpenAIcache$1.75$14.0099.2%
Azurecache$1.75$14.00

Specifications

Context window400K
Max output128K
Knowledge cutoff
Input modalitiestext, image
Output modalitiestext
Prompt cachingSupported
Cache read price$0.175/M
ModeratedYes

GPT-5.2-Codex FAQ

How much does GPT-5.2-Codex cost?

GPT-5.2-Codex costs $1.75 per million input tokens and $14.00 per million output tokens via OpenRouter, making it 236th cheapest of 298 paid models.

How smart is GPT-5.2-Codex?

GPT-5.2-Codex scores 49.0 on the Artificial Analysis Intelligence Index, ranking 17th of 178 benchmarked models, with a GPQA Diamond score of 90%.

How fast is GPT-5.2-Codex?

GPT-5.2-Codex generates around 63 tokens per second with 1.5s time-to-first-token (p50), the 130th fastest tracked model.

What is GPT-5.2-Codex's context window?

GPT-5.2-Codex supports a 400K-token context window and can output up to 128K tokens. It accepts text, image input.

Compare head-to-head