Do coding agents recommend i18next?
i18next was chosen in 5% of 500 judged internationalization sessions, ranking sixth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
i18next was chosen in 5% of 500 judged internationalization sessions, ranking sixth. It was also raised as a candidate in 157 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 i18next. What an agent actually installed.
The numbers
| Category | Internationalization |
| Sessions in the category | 500 |
| Sessions where i18next was chosen | 27 |
| Install share | 5% |
| Rank in category | 6 of 31 |
| Codebases it won in | 3 |
| Raised as a candidate, not chosen | 157 |
| Chosen when considered | 15% |
| Site | i18next.com |
By agent
Claude Code, Codex, Cursor and Muse Code land within 9 points of each other on i18next, 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 i18next | Share |
|---|---|---|---|
| Claude Code | 113 | 7 | 6% |
| Codex | 150 | 15 | 10% |
| Cursor | 103 | 1 | 1% |
| Grok Build CLI | 26 | 1 | 4% |
| Muse Code | 108 | 3 | 3% |
By who was asking
i18next does much better with one kind of buyer than another. It won 21% of sessions asked as vibe coder and 0% of those asked as senior engineer.
| Who is asking | Sessions | Chose i18next | Share |
|---|---|---|---|
| Vibe coder | 102 | 21 | 21% |
| Junior developer | 115 | 1 | 1% |
| Senior engineer | 113 | 0 | 0% |
| Enterprise team | 170 | 5 | 3% |
What i18next was up against
The full ranking in internationalization, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | next-intl | 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 (this page) | 27 | 5% |
What this means
This is an integration problem, not a presence problem. Agents raised i18next in 157 sessions and chose it in 27, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
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 i18next: 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 i18next?
Yes. i18next was chosen in 27 of the 500 judged sessions in internationalization, a 5% install share, ranking sixth in its category.
Does Claude Code recommend i18next?
In 7 of the 113 sessions in internationalization run with Claude Code, which is 6%.
Do different coding agents treat i18next differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 1% and 10% of their runs.
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 i18next considered but not chosen?
It was raised as a candidate in 157 sessions without being chosen, and chosen in 27. That is a 15% 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.