Codex
OpenAI's coding agent — runs in CLI, IDE, and cloud-hosted runtimes. Drives the Plus/Pro coding workflow.
Capabilities
- terminal
- file_io
- shell_exec
- cloud_runtime
Benchmarks
| Benchmark | Score | Underlying model | Measured | Source |
|---|---|---|---|---|
| SWE-bench Verified | 85.0% | gpt-5-3-codex | Apr 20, 2026 | link ↗ |
| Terminal-Bench 2.0 | 77.3% | gpt-5-3-codex | Apr 22, 2026 | link ↗ |
| SWE-bench Pro | 56.8% | gpt-5-3-codex | Apr 22, 2026 | link ↗ |
Usage signals
No public usage data recorded yet. See the OpenRouter usage leaderboard for cross-agent comparisons.
Pricing & license
- Pricing
- Included with ChatGPT Plus/Pro
Base models
Compare Codex with…
Related news
How ChatGPT Work helps Stampli move ideas to market
Stampli used Codex and ChatGPT Work to compress weeks of launch production into days when it had a fixed deadline and its design resources were already committed elsewhere. This shows how AI tools can help teams ship ideas faster under tight constraints without waiting on additional design capacity.
Asana cleared 5 years of engineering work in 2 weeks with Codex
Asana used OpenAI Codex to replace an outdated testing system in two weeks, finishing work the company had estimated would take five years for about $12,000. The result highlights how code-generation tools can compress large engineering projects by orders of magnitude when the task is well scoped.
From assistance to execution: How enterprises put AI to work
OpenAI research says enterprises are moving from simple AI assistance to agentic execution with ChatGPT and Codex, while frontier firms are adopting these tools faster than the rest. The shift matters because it signals AI is being used to carry out work rather than just help with it, creating a widening gap between early adopters and laggards.
How RingCentral builds AI-native work from engineering to ops
RingCentral is using ChatGPT Work and Codex to speed up AI product development and to centralize operational intelligence across its engineering and operations teams. The notable detail is that it is applying these tools across both engineering and ops, signaling a broader move toward AI-native workflows rather than isolated coding assistance.
New ways to learn and teach with ChatGPT Work and Codex
OpenAI is introducing new education plugins for ChatGPT Work and Codex aimed at K–12 teachers, college educators, and students to support learning, teaching, research, and building. The update expands the tools’ classroom and coding use cases, signaling a broader push to integrate AI into education workflows.
Circles powers telco personalization with OpenAI technology
Circles uses the OpenAI API and Codex to power AI-native telco experiences, reporting a 22% increase in ARPU, a 9% reduction in churn, and improved development efficiency. The results show how applying OpenAI tools to telecom personalization can directly move core business metrics while also speeding up engineering workflows.
Apple’s OpenAI lawsuit is about who gets to define the post-smartphone era
Apple has sued OpenAI over alleged trade-secret theft, saying ex-Apple employees at OpenAI sought hardware manufacturing details in job interviews and may have downloaded files from Apple servers, while OpenAI denies the claims. The case matters because Apple is a notoriously relentless litigant and OpenAI, despite spending $6.5 billion to buy Jony Ive’s io Products in 2025, is still cash-burning and could be distracted at a critical moment in the post-smartphone hardware race.
Building AI infrastructure with the Effingham County community
OpenAI announced Project Camellia in Effingham County, Georgia, with commitments around responsible energy use, community investment, job creation, and access to Codex. The project ties AI infrastructure expansion to local economic benefits and developer access, signaling how major model deployments are being paired with regional policy and community commitments.