GILD verdict
Choose Codex when a company buys the agent, because ChatGPT Business and Enterprise add SSO and audit logs that Jules lacks.
Choose Jules for individual developers who want a free or Google AI plan allowance of scoped GitHub tasks, scheduled maintenance, and automatic CI fixes. On public GitHub, PR Arena counts 90.4% of Codex's ready pull requests as merged and 84.0% of Jules's (October 28, 2026). Trial both on the same scoped tasks and compare merged pull requests per reviewer hour.
Paid Jules plans attach only to personal Google accounts, which leaves Codex as the only one of the two a company can buy and administer. Each agent takes a delegated task, works in a cloud environment built from GitHub repositories, and hands back a change to review. Jules caps tasks per rolling 24 hours, and Codex meters messages and cloud tasks against the plan allowance.
Choosing between Jules and Codex
Choose Jules if
- You want a free tier with a fixed daily task count to evaluate delegated work.
- Developers on personal Google accounts want Google AI Pro's 100 tasks per rolling 24 hours, at US$19.99 per month.
- You want recurring tasks on a schedule and automatic fixes for failing GitHub Actions checks on the agent's own pull requests.
Choose Codex if
- Your company buys ChatGPT Business or Enterprise and needs SAML SSO, RBAC, or Compliance API audit logs.
- Engineers want the same agent in a terminal CLI, an IDE extension, and the desktop app as well as in the cloud.
- You want an automatic code review pass on GitHub pull requests from the same plan.
Side by side
| Dimension | Jules | Codex |
|---|---|---|
| How you buy it | Free plan, or included with Google AI Pro and Ultra on personal @gmail.com accounts | Included with ChatGPT Plus, Pro, Business, Enterprise, and Edu; Free and Go get the desktop app as it rolls out |
| Individual priceList prices in US dollars. Jules counts tasks and Codex counts usage that varies by model and task, so included work is not directly comparable. | Google AI Pro: US$19.99 per month or US$199.99 per year | ChatGPT Plus: US$20 per month |
| Team plan | None; Workspace and business accounts cannot buy paid Jules plans | ChatGPT Business: US$20 per user per month billed annually for 2 or more users, or US$25 billed monthly |
| Usage limits | Free 15 tasks per rolling 24 hours (3 at once); Pro 100 (15); Ultra 300 (60) | Local messages and cloud tasks share the plan allowance; Plus and Business estimate 15 to 160 local messages per five hours on GPT-6.1 Sol, and cloud tasks use more |
| Where work runs | A fresh Google Cloud VM per task, with internet access | An isolated workspace per task from a published cloud environment, with internet access and allowed domains set per environment |
| Where tasks start | Web app, Jules Tools CLI, alpha REST API, GitHub Action, and GitHub issues labeled jules | ChatGPT on the web, mobile, and desktop, the Codex CLI, and the IDE extension |
| Data and admin | Google states Jules does not train on private repository content; no admin console or SSO | Business: no training on business data by default, SAML SSO, MFA; Enterprise adds SCIM, RBAC, and Compliance API audit logs |
| Merged pull requests on public GitHubPR Arena's count of pull requests each agent opened on public GitHub, updated October 28, 2026. Ready means the pull request left draft. | 84.0% of 245,534 ready pull requests12 | 90.4% of 8,241,874 ready pull requests12 |
What practitioners report, side by side
Each product's figures come from its own practitioners, for the group you pick.
Overall signal
All practitioners rate Codex +44, 44 points above Jules at 0. Most of the gap is in complaints, with 24 of Jules's 68 sources negative against 12 of Codex's 106.
The score counts the authors from all practitioners that take a side, one vote each with their latest view, and is how far positive votes lead negative ones, per 100 votes, so Jules's 0 rests on votes split 24 positive, 18 mixed and 24 negative and Codex's +44 on 55, 30 and 12.
A lead of a fifth of the votes reads positive and a lead of half strong positive, with the same lines below zero. The dots show each source, positive, mixed, negative. Use a task pilot to measure accepted work and review time.
Footprint on the Agentic Software Development stack
They differ on three of 12 layers. Codex owns two that Jules does not. Coverage is each product's placement on this stack, as its product page shows it. Core is a job the product owns; Supports and Touches are jobs it helps with. Coverage says nothing about how well a product does them.
| Layer | Jules | Codex |
|---|---|---|
| Build | ||
| Codebase context | Supports | Core |
| Agent runtime | Supports | Core |
| Validate | ||
| Code review | Touches | Supports |
The 9 layers where they match
| Layer | Jules | Codex |
|---|---|---|
| Plan | ||
| Work planning | Supports | Supports |
| Build | ||
| Coding | Core | Core |
| Tool execution | Core | Core |
| Validate | ||
| Debugging | Supports | Supports |
| Testing | Supports | Supports |
| Application security | Touches | Touches |
| Ship | ||
| Source control | Touches | Touches |
| CI/CD | Touches | Touches |
| Operate | ||
| Observability | Touches | Touches |
What practitioners praise
Among all practitioners, Codex alone has seven praise themes that reach 5 sources from 3 authors. Code Quality and Pull Request Review lead, at 27 of 33 and 12 of 12. Both carry Developer experience. It is praised in 5 of the 10 Jules sources that discuss it, against 20 of 36 for Codex. Jules alone has four praise themes that reach 5 sources from 3 authors. End-to-end execution and Async delegation lead, at 17 of 17 and 14 of 14.
| Praised for | Jules | Codex |
|---|---|---|
| Developer experience | 5 of 10 | 20 of 36 |
| End-to-end execution | 17 of 17 | Not a theme in its sources |
| Async delegation | 14 of 14 | Not a theme in its sources |
| Free tier & plan value | 11 of 12 | Not a theme in its sources |
| Maintenance & chores | 6 of 6 | Not a theme in its sources |
| Code Quality | Not a theme in its sources | 27 of 33 |
| Pull Request Review | Not a theme in its sources | 12 of 12 |
| Long-Running Autonomy | Not a theme in its sources | 12 of 17 |
| Value for Money | Not a theme in its sources | 11 of 15 |
| Codebase Understanding | Not a theme in its sources | 10 of 11 |
| Fast Runs | 2 of 3 so far | 6 of 12 |
| Stability | Not a theme in its sources | 1 of 6 |
Each count is the sources that praise a theme, or raise it as a concern, out of those that discuss it. A row pairs the two products when both carry a theme under the same or an equivalent name.
A count ending in "so far" has under 5 sources from 3 authors among all practitioners. "Not a theme in its sources" means GILD found no theme of that name in that product's sources.
What practitioners raise as concerns
Jules's sources raise Requires strong review more often than Codex's. It is raised in 19 of the 20 Jules sources that discuss it, against 9 of 23 for Codex. Jules alone has four concern themes that reach 5 sources from 3 authors. Unreliable task completion and GitHub workflow friction lead, at 24 of 25 and 10 of 12. Codex alone has four concern themes that reach 5 sources from 3 authors. Usage Limits / Cost and Inconsistent Results lead, at 22 of 39 and 15 of 16.
| Raised as a concern | Jules | Codex |
|---|---|---|
| Requires strong review | 19 of 20 | 9 of 23 |
| Needs Close Steering | 3 of 7 | 6 of 9 |
| Unreliable task completion | 24 of 25 | Not a theme in its sources |
| GitHub workflow friction | 10 of 12 | Not a theme in its sources |
| Task speed | 8 of 9 | Not a theme in its sources |
| VM environment setup | 5 of 5 | Not a theme in its sources |
| Usage Limits / Cost | Not a theme in its sources | 22 of 39 |
| Inconsistent Results | Not a theme in its sources | 15 of 16 |
| Speed | Not a theme in its sources | 13 of 22 |
| Communication & Steering | Not a theme in its sources | 7 of 12 |
12 sources
- Jules docs: Limits and plans
- Google One: Google AI plans and Jules limits
- Jules docs: FAQ
- Jules docs: Managing tasks and repos
- Jules docs: Scheduled tasks
- Jules changelog: CI Fixer and commit authoring (Feb 19, 2026)
- Jules docs: REST API quickstart (alpha)
- Codex docs: Pricing
- Codex docs: Cloud
- Codex docs: GitHub code review
- Codex docs: Cloud environments
- PR Arena: AI coding agent pull request leaderboard (updated Oct 28, 2026 UTC)