OpenAI: GPT-5 Codex
Analysis Summary
GPT-5 Codex is OpenAI's coding-focused frontier model, with an intelligence index of 44.6, coding index of 38.9, and agentic index of 62.4. Math performance is exceptional at 98.7, and GPQA at 0.837 and MMLU Pro at 0.865 reflect strong general reasoning. Vision, tool use, and function calling are all supported across a 400K context window, making it one of the most capable all-round models in this batch.
For businesses, GPT-5 Codex is well-suited to autonomous coding agents, complex multi-step workflows, long-document analysis, and client-facing content where accuracy is critical. The agentic index of 62.4 places it among the top performers in the broader field for agent reliability. Instruction following (ifbench 0.741) and long-context reasoning (lcr 0.690) are both strong. The main trade-off is cost: at $1.25 input and $10.00 output per million tokens, it is expensive for high-volume use.
Best adopted for high-value tasks where reasoning depth, coding accuracy, and agentic reliability justify the premium. Pair with a cheaper model for routine or bulk workloads.
Assessed June 6, 2026
Editorial notes
GPT-5 Codex from OpenAI delivers an intelligence index of 44.6, a coding index of 38.9, and an agentic index of 62.4, with vision, tool use, and a 400K context window for demanding business workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How OpenAI: GPT-5 Codex compares
OpenAI: GPT-5 Codex ranks #35 of 377 AI models we track for overall intelligence, #43 of 314 for coding, #46 of 289 for agentic tasks. Its 400K-token context window is larger than 85% of the models we list. At $1.25 per million input tokens it is cheaper than 21% of comparable models.
About OpenAI: GPT-5 Codex
GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does OpenAI: GPT-5 Codex stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
openai/gpt-5-codex
|
| Provider | openai |
| Release Date | September 23, 2025 |
| Context Length | 400,000 tokens |
| Max Completion | 128,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.25 | $0.001250 |
| Output | $10.00 | $0.010000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about OpenAI: GPT-5 Codex
How much does OpenAI: GPT-5 Codex cost?
OpenAI: GPT-5 Codex costs $1.25 per million input tokens and $10.00 per million output tokens.
What is the context window of OpenAI: GPT-5 Codex?
OpenAI: GPT-5 Codex has a context window of 400,000 tokens (400K).
Is OpenAI: GPT-5 Codex good for coding?
On our coding benchmark index, OpenAI: GPT-5 Codex ranks #43 of 314 models, placing it in the top quartile of the field for code generation and debugging.
What can OpenAI: GPT-5 Codex do?
OpenAI: GPT-5 Codex supports image/vision input, tool use, and function calling.
Who created OpenAI: GPT-5 Codex?
OpenAI: GPT-5 Codex is developed by OpenAI and was released on September 23, 2025.
