VIETHOANG.US

Hardware & Phone

Gaming & Desk Setup

  • Esports Mice
  • Custom Keyboardssoon
  • OLED Monitorssoon
  • Ergonomic Chairssoon
AI Developer CLI & Agentic WorkflowsAi DevLandscape checked 3 Sep 2026

Claude Code vs OpenAI Codex: Which Coding Agent Belongs in Your Daily Workflow?

Two terminal-first coding agents, one workflow decision. How each handles a repository you care about, what happened to Canvas and the o-series, and which one to put in front of a team.

Viet HoangEditor
Published July 22, 202610 min read

The Bottom Line (30-Second Verdict)

Winner: Claude Code· 9.2/10

Claude Code is the better companion for a long session inside one repository you care about — it is calmer about large context, and its permission model makes it safe to leave running. Codex is the better tool for handing a task off and walking away, because OpenAI ships a cloud agent alongside the CLI and the CLI itself is open source. The old framing of this fight — Canvas and the o-series — is out of date: Canvas is being retired from OpenAI's newest models, and the o-series has been folded into GPT-5-generation thinking modes.

Best long-session behaviour

Claude Code

9.2/10
  • Agentic search means you do not hand-pick which files it may look at
  • Per-tool permission prompts make it genuinely safe to leave running on a real repo
Read the setup docs · $20/mo
Strongest cloud handoff

OpenAI Codex

8.7/10
  • The CLI is genuinely open source, so you can read the loop and pin your own build
  • A cloud agent runs longer tasks without holding your laptop hostage
Read the Codex CLI docs · $20/mo

Side by side

Head-to-head metrics

Getting started

How each one gets onto your machine

Straight from vendor documentation. Codex is a single npm install; Claude Code deliberately avoids requiring Node at all.

Claude CodeInstaller, Homebrew, WinGet, apt/dnf/apk, npm
OpenAI Codexnpm i -g @openai/codex
Access

What subscription you need

Neither agent is available on its vendor's free tier. Both start at $20/month on a plan you may already hold.

Claude CodePro, Max, Team, Enterprise or API (tied)
OpenAI CodexChatGPT Plus and above, or API (tied)
Where work runs

Local session vs delegated task

The clearest structural difference. One is built around staying in the room with you; the other is built around leaving.

Claude CodeLocal terminal session
OpenAI CodexLocal CLI, IDE or cloud agent

First, the framing has changed

If you last read a comparison of these tools a year ago, it was probably framed as Claude Code vs Canvas and o3-mini. That framing has aged badly, and it is worth correcting before anything else, because a lot of buying advice still repeats it.

Canvas — ChatGPT’s side-panel document and code editor — is still reachable on Free, Plus and Pro plans, but OpenAI has begun retiring it from its newest models in favour of writing blocks and code blocks rendered inline in the chat itself. The o-series reasoning models that used to be quoted alongside it have been folded into the GPT-5 generation’s thinking modes rather than sold as separate names.

So the real comparison in September 2026 is not an editor pane against a terminal. It is two agentic coding products: Claude Code and OpenAI Codex. Both live in your terminal, both read and edit files, both run commands. That is the fight.

What we are not going to tell you

You will find sites quoting these tools’ SWE-bench percentages, “context retention” scores and token-per-second figures to two decimal places. We do not run those evaluations, and neither, in most cases, do the sites quoting them — the numbers are lifted from vendor announcements and then presented as independent testing.

What follows is published capability, published pricing, and our opinion from using both on this site’s own codebase. The scores at the top of this page are editorial judgement on a ten-point scale. They are an argument, not a measurement.

Installation and access

Claude Code goes out of its way not to be an npm package. Anthropic’s documentation leads with a native installer (curl -fsSL https://claude.ai/install.sh | bash), and also publishes a Homebrew cask, a WinGet package, and signed apt, dnf and apk repositories, with npm as an option rather than the default. It runs on macOS 13+, Windows 10 1809+, and mainstream Linux distributions, and it requires a Pro, Max, Team, Enterprise or Console account — the free Claude plan does not include it.

Codex is the simpler story: npm i -g @openai/codex, and the client is Apache-2.0 licensed on GitHub. Access comes with ChatGPT Plus and above; OpenAI’s cheapest paid Go tier excludes it.

For an individual that is a shrug. For a locked-down corporate fleet it is the whole conversation: a signed apt repository is easier to get past a platform team than a global npm install, and an Apache-2.0 client is easier to get past a security review than a closed binary. The two win that argument in opposite directions.

Living in one repository

This is where Claude Code earns its place for us. Its agentic search means you do not curate a context window by hand — you ask a question about the project and it goes and finds the files. Over a long session on a codebase with a lot of history, that difference compounds: less time spent being a librarian for your assistant.

The permission model matters as much as the search. Because it asks before running commands and can be scoped per tool, you can leave it working without the low-grade anxiety of wondering what it just did to your working tree. Project-level configuration lives in version control, so a team can standardise how the agent behaves in the same review process as everything else.

The cost is real: long sessions consume plan limits quickly, and the $20 Pro tier runs dry faster than most people expect. Budget for a Max tier if this becomes your default way of working.

Handing work off

Codex’s structural advantage is that it does not assume you are sitting there. Alongside the CLI and the IDE extension, OpenAI runs a cloud agent you can delegate a task to and collect later. For the class of work that is well-specified and boring — mechanical migrations, dependency bumps, test scaffolding across many files — that is a genuinely different shape of tool, and Claude Code has no direct equivalent.

It is also the harder half to get right. A delegated run is only as good as the environment definition you gave it; an agent that cannot reproduce your build fails in ways that cost more time than doing the task yourself. Budget for configuring it.

Who should buy which

Buy Claude Code if most of your week is spent inside one substantial codebase, if you want the agent’s behaviour codified in the repo, or if your platform team would rather install a signed OS package than a global npm module. It is the better default for a working developer, and it is what this site is built with.

Buy OpenAI Codex if you already pay for ChatGPT and want to stop paying twice, if an open-source client is a hard requirement for review, or if the work you most want automated is the kind you would rather hand off than supervise.

Buy both — $20 each at entry, no conflict, and the honest answer after several months is that we reach for Claude Code to think through a change and Codex to grind through one. That is $40 a month to stop arguing, which beats a bad standardisation decision.

VietHoang.us is not affiliated with, or paid by, Anthropic or OpenAI. The links on this page go to official product and documentation pages.

Benchmark 01

Workflow matrix

Published capabilities as of 3 September 2026. Both products ship weekly — verify anything you are about to standardise a team on.

CapabilityClaude CodeOpenAI Codex
Runs in a plain terminalYesYes
Open source clientNoYes (Apache-2.0)
Cloud agent for delegated tasksNoYes
Installs without Node.jsYesnpm required
Signed OS package repositoriesapt, dnf, apk, Homebrew, WinGetnpm
Per-tool permission promptsYesApproval modes
Repo-level config in version controlCLAUDE.md + settings.jsonAGENTS.md + config
Included on vendor free tierNoNo
Entry subscription (list)$20/mo Claude Pro$20/mo ChatGPT Plus

Live verified pricing & reader coupons

Updated July 22, 2026
Claude Code
$20/moClaude Pro list price · Max tiers at $100 and $200/mo

Sold by Anthropic

Read the setup docs

Official product page · not an affiliate link

OpenAI Codex
$20/moChatGPT Plus list price · Pro tier at $200/mo

Sold by OpenAI

Read the Codex CLI docs

Official documentation · not an affiliate link

Affiliate disclosure: VietHoang.us earns a commission on qualifying purchases made through the links above. Units are bought at retail and no placement in this comparison is paid for.

Viet Hoang

Editor

Viet Hoang runs the head-to-head comparisons published on VietHoang.us. Every unit in this article was bought at retail — no review samples, no sponsored placement — and the scores, tables and prices are revised when a product is re-tested or repriced.

Related showdowns