modelgrep
O

OpenAI: GPT-5.2

openai/gpt-5.2

63rd smartest of 180ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
33.6
63rd of 180
Design Elo
1264
Game Dev
Speed
42
197th fastest
Latency
2.8s
first token
Input price
$1.75
238th cheapest
Context
400K
128K max out

How it compares

Smarter than65%
of all ranked models
Faster than36%
of all ranked models
Cheaper than20%
of all ranked models

Overview

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

Benchmarks

independent · via OpenRouter
Artificial Analysis61th percentile
Intelligence Index
33.6
Coding Index
34.7
Agentic Index
39.5
GPQA Diamond
71%
Humanity's Last Exam
7%
SciCode
40%
Tau²-Bench (agentic)
47%
Design Arena · Elo13,530 tournaments
Game Dev
1264
Data Viz
1231
Website
1222
codecategories
1218
UI Component
1215
asciiart
1195
svg
1193
godotgamedev
1183
mobileapps
1182
webapps
1171
3D
1148
fullstack
1121
androidnative
1080

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
OpenAIcache$1.75$14.0099.8%
Azurecache$1.75$14.00100%

Specifications

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

GPT-5.2 FAQ

How much does GPT-5.2 cost?

GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens via OpenRouter, making it 238th cheapest of 298 paid models.

How smart is GPT-5.2?

GPT-5.2 scores 33.6 on the Artificial Analysis Intelligence Index, ranking 63rd of 180 benchmarked models, with a GPQA Diamond score of 71%.

How fast is GPT-5.2?

GPT-5.2 generates around 42 tokens per second with 2.8s time-to-first-token (p50), the 197th fastest tracked model.

What is GPT-5.2's context window?

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

Compare head-to-head