Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
GPT-5.3-Codex
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Pricing
Evaluations
Evaluation overview
Overall rank
#35
79.2 points · 180 models
Agents rank
#25
80.4 points · 125 models
Data coverage
14 items
4 sources · updated through 2026-07-16
Domain performance
Coding
#35 / 160
79.9
Research
#37 / 174
88.1
Agents
#25 / 125
80.4
Evaluation highlights
All evaluations
SWE-lancer IC Diamond
Coding · OpenAI GPT-5.3-Codex Release
81.4%
1
/ 12
GPQA-Diamond
Reasoning · OpenAI GPT-5.4 Release
92.6%
13
/ 126
CTF Challenge
Cybersecurity · OpenAI GPT-5.3-Codex Release
77.6%
1
/ 3
Toolathlon
Agents · OpenAI GPT-5.4 Release
51.9%
9
/ 26
Terminal-Bench 2.0
Coding · OpenAI GPT-5.4 Release
77.3%
2
/ 10
Arena WebDev Rating
Coding · Arena.ai WebDev · Codex-harness mode
1,406.61Elo
40
/ 88
Basic information
Context (input / output)
400K / 128K
Release date
2026-02
Input modalities
Text · Image
Output modalities
Text
Availability
OpenAI
Full pricing
Input
$1.75 /1M
Output
$14 /1M
Related links
Official site