Do coding agents recommend next-intl?
next-intl is the most chosen internationalization solution, taking 22% of 500 judged internationalization sessions.
next-intl is the most chosen internationalization solution, taking 22% of 500 judged internationalization sessions. It was also raised as a candidate in 28 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in internationalization inside a realistic codebase. Not what a chat assistant says about next-intl. What an agent actually installed.
The numbers
| Category | Internationalization |
| Sessions in the category | 500 |
| Sessions where next-intl was chosen | 110 |
| Install share | 22% |
| Rank in category | 1 of 31 |
| Codebases it won in | 4 |
| Raised as a candidate, not chosen | 28 |
| Chosen when considered | 80% |
| Site | next-intl.dev |
By agent
Claude Code, Codex, Cursor and Muse Code land within 13 points of each other on next-intl, which is closer than most products in this experiment manage. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose next-intl | Share |
|---|---|---|---|
| Claude Code | 113 | 34 | 30% |
| Codex | 150 | 32 | 21% |
| Cursor | 103 | 22 | 21% |
| Grok Build CLI | 26 | 4 | 15% |
| Muse Code | 108 | 18 | 17% |
By who was asking
next-intl does much better with one kind of buyer than another. It won 50% of sessions asked as senior engineer and 0% of those asked as junior developer.
| Who is asking | Sessions | Chose next-intl | Share |
|---|---|---|---|
| Vibe coder | 102 | 45 | 44% |
| Junior developer | 115 | 0 | 0% |
| Senior engineer | 113 | 56 | 50% |
| Enterprise team | 170 | 9 | 5% |
What next-intl was up against
The full ranking in internationalization, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | next-intl (this page) | 110 | 22% |
| 2 | Django translation framework | 96 | 19% |
| 3 | Symfony Translation | 41 | 8% |
| 4 | Paraglide JS | 41 | 8% |
| 5 | Built in-house (no product adopted) | 41 | 8% |
| 6 | Rails I18n | 38 | 8% |
| 7 | Vue I18n | 27 | 5% |
| 8 | i18next | 27 | 5% |
What this means
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
Where these numbers come from
The 500 sessions in internationalization are part of a published set of 15,051, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every internationalization run can be replayed on the board.
If you work on next-intl: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend next-intl?
Yes. next-intl was chosen in 110 of the 500 judged sessions in internationalization, a 22% install share, ranking first in its category.
Does Claude Code recommend next-intl?
In 34 of the 113 sessions in internationalization run with Claude Code, which is 30%.
Do different coding agents treat next-intl differently?
Yes, and by a wide margin. Claude Code chose it in 30% of its runs and Muse Code in 17%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is next-intl considered but not chosen?
It was raised as a candidate in 28 sessions without being chosen, and chosen in 110. That is a 80% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.