modelgrep
O

OpenAI: GPT-5.5

openai/gpt-5.5

5th smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
56.7
5th of 178
Design Elo
1354
Game Dev
Speed
36
213th fastest
Latency
2.8s
first token
Input price
$5.00
275th cheapest
Context
1.1M
128K max out

How it compares

Smarter than97%
of all ranked models
Faster than28%
of all ranked models
Cheaper than8%
of all ranked models

Overview

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

Benchmarks

independent · via OpenRouter
Artificial Analysis97th percentile
Intelligence Index
56.7
Coding Index
56.2
Agentic Index
69.4
GPQA Diamond
93%
Humanity's Last Exam
41%
SciCode
54%
Tau²-Bench (agentic)
92%
Design Arena · Elo16,275 tournaments
Game Dev
1354
asciiart
1309
UI Component
1298
codecategories
1298
Data Viz
1296
Website
1294
svg
1286
3D
1262
androidnative
1259
mobileapps
1239
godotgamedev
1218
agenticgamedev
1211
webapps
1192
agenticslides(python-pptx)
1168
fullstack
1167
agenticslides
1150
agentichtmlslides
1084
agenticslides(html)
1077

Providers & pricing (3)

ProviderIn $/MOut $/MUptime
OpenAI$5.00$30.0099.2%
Azure$5.00$30.0099.9%
Azure$5.50$33.00

Specifications

Context window1.1M
Max output128K
Knowledge cutoffDec 2025
Input modalitiesfile, image, text
Output modalitiestext
Prompt caching
Cache read price$0.500/M
ModeratedYes

GPT-5.5 FAQ

How much does GPT-5.5 cost?

GPT-5.5 costs $5.00 per million input tokens and $30.00 per million output tokens via OpenRouter, making it 275th cheapest of 298 paid models.

How smart is GPT-5.5?

GPT-5.5 scores 56.7 on the Artificial Analysis Intelligence Index, ranking 5th of 178 benchmarked models, with a GPQA Diamond score of 93%.

How fast is GPT-5.5?

GPT-5.5 generates around 36 tokens per second with 2.8s time-to-first-token (p50), the 213th fastest tracked model.

What is GPT-5.5's context window?

GPT-5.5 supports a 1.1M-token context window and can output up to 128K tokens. It accepts file, image, text input.

Compare head-to-head