Claude Code vs OpenAI Codex
Claude Code (Anthropic) and OpenAI Codex (OpenAI) side by side on public data, as of Nov 20, 2026.
OpenAI Codex has 1.4x the weekly package downloads of Claude Code (26.6M against 18.9M). Claude Code has 1.8x the VS Code extension installs of OpenAI Codex (30.6M against 16.9M). Claude Code and OpenAI Codex are close on GitHub stars (156K and 136K). Over the last 30 days downloads moved +16% for Claude Code and +7% for OpenAI Codex. Claude Code shipped 72 stable releases in the past 90 days.
Which should you choose?
Choose Claude Code if
- benchmark results matter to you: 65.8% on Terminal-Bench against 62.1%
Choose OpenAI Codex if
- you want to start free: it has a free plan, Claude Code does not
- you want code you can read, fork or self-host (Apache-2.0)
- you need to run local models
- steady service matters most: 1 incident on its status page in 30 days against 15
Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.
Side-by-side numbers
| Metric | Claude Code | OpenAI Codex |
|---|---|---|
| Gid Score | 88 | 84 |
| Usage data as of | Nov 19 | Nov 19 |
| Rank by Gid Score | #1 | #2 |
| Downloads, last 7 days | 18.9M | 26.6M |
| Downloads, 7-day change | up 15.1% | up 2.4% |
| Downloads, 30-day change | up 15.5% | up 7.4% |
| VS Code installs | 30.6M | 16.9M |
| Marketplace rating | 3.7 / 5 (936) | 2.7 / 5 (975) |
| GitHub stars | 156K | 136K |
| Homebrew installs, 30 days | 61.7K | 529K |
| Hacker News mentions, 30 days | 1,889 | 1,429 |
| Latest stable release | 2.1.328 · yesterday | 0.168.0 · 7d ago |
| Stable releases, 90 days | 72 | — |
| Terminal-Bench (best run) | 65.8% · v4.1 | 62.1% · v4.1 |
| Price | $20/mo | Free + $8/mo |
| Usage limits | Pro and Max: a 5-hour session limit plus a weekly limit; Ultra: a weekly limit only (verified Ultra accounts have no 5-hour limit) Pro: More usage than Free every 5 hours and every week ($17/month with yearly billing); the plans page gives no message counts all plans | 5-hour limit, weekly limits may apply Go: GPT-6 Luna in the desktop app; limits not published all plans |
| Incidents, last 30 days | 15 · 11 major or critical | 1 |
| License | Proprietary | Apache-2.0 |
| First released | February 2025 | April 2025 |
| Interfaces | CLI, IDE extension, Desktop, Web, Mobile, SDK | CLI, IDE extension, Desktop, Web, Mobile, SDK |
| Models | Anthropic Claude models via Claude plans, a Console API key or supported third-party cloud providers | OpenAI GPT models (GPT-6 family per current docs) via ChatGPT sign-in or an OpenAI API key |
A dash means there is no public data for that metric as of Nov 20, 2026.
Trends
Claude Code
Anthropic's agentic coding tool that reads a codebase, edits files and runs commands from the terminal, with VS Code and JetBrains integrations plus desktop, web and mobile access. It runs Claude models through a Claude subscription, an Anthropic Console API key or supported third-party cloud providers.
Pricing: Claude Code is included in Pro ($17/month annual or $20/month monthly), Max ($100/month), and Ultra ($200/month) plans. The Free plan does not include Claude Code. Team plans offer standard seats at $20/seat/month annual ($25 monthly) and premium seats at $100/seat/month annual ($125 monthly), both with Claude Code. Enterprise seats cost $20/seat/month annual (20 seat minimum) plus usage at API rates.
Latest release 2.1.328:
- Added auto mode for Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and Claude apps gateway; interactive sessions with no permission mode start in it
- Added "onFailure": "block" for mcp_tool hooks, as for command and HTTP hooks: a hook whose call fails blocks the action
- Added a warning when a message from a session that skips permission prompts may be held and dropped by a cloud session
- Added a notice in /status and claude doctor when an OpenTelemetry exporter has no endpoint and its data would likely be lost
OpenAI Codex
OpenAI's coding agent, offered as an open-source terminal CLI, an IDE extension, a desktop app and a cloud agent that works on repositories. Users sign in with a ChatGPT account or use an OpenAI API key; with an API key, Codex works in the CLI, SDK and IDE extension without cloud features such as GitHub code review and Slack. On the Free and Go plans Codex runs in the desktop app (subject to rollout); the web, CLI and IDE extension come with Plus and higher.
Pricing: Included in ChatGPT plans: Free $0, Go $8/month, Plus $20/month, Pro from $100/month ($100, $200 or $500 tiers), Business $20/user/month billed annually ($25 monthly), Enterprise and Edu by contact. API-key use is billed at API rates (no cloud features).
Latest release 0.168.0:
- Browse model providers under Sessions → Model providers and choose the default for new chats.
- Enable features.tui_workspace to view a side conversation beside the main chat. Drag the divider to resize the panes or press leader z to zoom the focused pane.
- Attach recordings when using an audio-capable model. Codex skips confirmed rejected recordings on later turns and uses clip duration to keep more short recordings in context.
- Enable features.image_generation_animation to generate or edit animated GIFs with optional frame count and timing controls.
Claude Code vs OpenAI Codex: common questions
Is Claude Code or OpenAI Codex cheaper?
OpenAI Codex has the lower entry price: paid plans from $8 a month against $20 for Claude Code, from the official pricing pages. OpenAI Codex also has a free option.
Is Claude Code or OpenAI Codex open source?
OpenAI Codex is open source (Apache-2.0); Claude Code is proprietary.
Which is more popular, Claude Code or OpenAI Codex?
Claude Code has a Gid Score of 88 against 84 for OpenAI Codex. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.
Do Claude Code and OpenAI Codex support local models?
OpenAI Codex documents support for local models; Claude Code's documentation does not.
Which has had fewer outages recently, Claude Code or OpenAI Codex?
In the last 30 days Claude Code's status page listed 15 incidents and OpenAI Codex's listed 1. Counts come from each official status page.