Home/Models/GPT-5.2-Codex
OpenAI logo

GPT-5.2-Codex

by OpenAI · Released Jan 2026

Multimodal
85.4
avg score
Rank #14
Compare
Better than 94% of all models
Context
400K tokens (~200 books)
Input $/1M
$1.75
Output $/1M
$14.00
Type
multimodal
License
Proprietary
Benchmarks
9 tested
Data updated today
About

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....

Tested on 9 benchmarks with 70.6% average. Top scores: LiveBench — Mathematics (88.8%), LiveBench — Coding (83.6%), LiveBench — Data Analysis (78.2%).

Looking for similar performance at lower cost?
GLM 5.1 scores 87.0 (102% as good) at $1.05/1M input · 40% cheaper
Capabilities
coding
67.6
#21 globally
reasoning
78.0
#14 globally
math
88.8
#7 globally
knowledge
74.3
#9 globally
agentic
41.0
#7 globally
language
70.1
#69 globally
Benchmark Scores
Compare All
Tested on 9 benchmarks · Ranked across 6 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

83.6
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

51.7
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

78.2
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

77.7
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

88.8
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
gpt-5-2-codex
Specifications
  • Typemultimodal
  • Context400K tokens (~200 books)
  • ReleasedJan 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.018
Available On
OpenAI logoOpenAI$1.75
Share & Export
Tweet
GPT-5.2-Codex is a proprietary multimodal AI model by OpenAI, released in January 2026. It has an average benchmark score of 85.4. Context window: 400K tokens.