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-5.2
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Pricing
Evaluations
Evaluation overview
Overall rank
#34
79.3 points · 180 models
Research rank
#19
92.7 points · 174 models
Data coverage
93 items
11 sources · updated through 2026-07-16
Domain performance
Coding
#36 / 160
78.7
Research
#19 / 174
92.7
Agents
#42 / 125
74.6
Vision
#28 / 65
81.7
Long context
#24 / 82
80.5
Evaluation highlights
All evaluations
AIME 2025
Reasoning · OpenAI GPT-5.2 Release
100%
1
/ 60
Graphwalks BFS 0K-128K
Long context · OpenAI GPT-5.4 Release
94%
1
/ 18
TAU2-Retail
Agents · OpenAI GPT-5.2 Release
82%
1
/ 18
MMMU
Multimodal · Qwen3.6-Plus Technical Report
86.7%
2
/ 25
SWE-bench Verified
Coding · Qwen3.5 Technical Report
80%
12
/ 60
CTF Challenge
Cybersecurity · OpenAI GPT-5.3-Codex Release
67.7%
2
/ 3
Basic information
Context (input / output)
400K / 128K
Release date
2025-12
Input modalities
Text · Image
Output modalities
Text
Availability
OpenAI
Full pricing
Input
$1.75 /1M
Output
$14 /1M
Related links
Official site
Version relationships
GPT-5.2 family
GPT-5.2
Current
2025-12 · Current model
GPT-5.2 Pro
2025-12 · Same series
GPT-5.2-Codex
2025-12 · Same series
Provider variants
Chat · Search / Non-Reasoning
Runtime modes
High