OpenAI: GPT-5.2-Codex
Analysis Summary
OpenAI GPT-5.2-Codex is a coding-focused model from OpenAI with an intelligence index of 40.1 and an agentic index of 64.6. Its scicode score of 0.546 and terminalbench hard score of 0.371 confirm strong performance on real-world software engineering tasks. The tau2 of 0.921 indicates high reliability on multi-step agentic workflows. Vision support and a 400K context window allow it to handle large codebases and image-based inputs simultaneously.
For businesses, this model is purpose-built for software engineering agents, automated code review, repository-level reasoning, and complex debugging pipelines. The large context window is a practical advantage for holding entire codebases in working memory. Instruction following (ifbench 0.776) and long-context reasoning (lcr 0.757) are both strong.
The main trade-off is cost: at $1.75 input and $14.00 output per million tokens, it is expensive and rewards high-value, low-volume tasks. Teams running autonomous coding agents or complex software workflows will find the capability justifies the price; for high-volume or routine tasks, a cheaper model is more appropriate.
Assessed June 30, 2026
Editorial notes
OpenAI GPT-5.2-Codex is a specialist coding and agentic model from OpenAI with an intelligence index of 40.1, strong agentic reliability (tau2 0.921), vision support, and a 400K context window built for software engineering workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How OpenAI: GPT-5.2-Codex compares
OpenAI: GPT-5.2-Codex ranks #29 of 385 AI models we track for overall intelligence, #43 of 293 for agentic tasks. Its 400K-token context window is larger than 85% of the models we list. At $1.75 per million input tokens it is cheaper than 17% of comparable models.
About OpenAI: GPT-5.2-Codex
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..
Capabilities
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does OpenAI: GPT-5.2-Codex stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
openai/gpt-5.2-codex
|
| Provider | openai |
| Release Date | January 14, 2026 |
| Context Length | 400,000 tokens |
| Max Completion | 128,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.75 | $0.001750 |
| Output | $14.00 | $0.014000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about OpenAI: GPT-5.2-Codex
How much does OpenAI: GPT-5.2-Codex cost?
OpenAI: GPT-5.2-Codex costs $1.75 per million input tokens and $14.00 per million output tokens.
What is the context window of OpenAI: GPT-5.2-Codex?
OpenAI: GPT-5.2-Codex has a context window of 400,000 tokens (400K).
What can OpenAI: GPT-5.2-Codex do?
OpenAI: GPT-5.2-Codex supports image/vision input, tool use, and function calling.
Who created OpenAI: GPT-5.2-Codex?
OpenAI: GPT-5.2-Codex is developed by OpenAI and was released on January 14, 2026.
