Agent leaderboards / All sectors / Internationalization

Internationalization: which solutions coding agents choose

next-intl leads internationalization with about 22% of runs.

500 runs12 apps5 agents4 personasupdated 2026-09-29

The interactive board, open on internationalization. Open it full page · this page as Markdown

Read this leaderboard as textrankings, key learnings, method

Key learningssummary

We asked 5 coding agents to add internationalization to 12 small apps, 500 runs in all, in several wordings and as 4 kinds of user. next-intl was chosen in 110 runs, about 22%. 32 of 58 cases changed their answer with the wording.

Explore every run in the interactive board

The ranking500 runs

	Product	Wins	Share
1	next-intlnext-intl.dev	110	22%
2	Django translation frameworkdocs.djangoproject.com	96	19%
3	Symfony Translationsymfony.com	41	8%
4	Paraglide JSinlang.com	41	8%
5	Built in-houseoutcome	41	8%
6	Rails I18nguides.rubyonrails.org	38	8%
7	Vue I18nvue-i18n.intlify.dev	27	5%
8	i18nexti18next.com	27	5%
9	FormatJSformatjs.github.io	15	3%
10	Tolgeetolgee.io	9	2%
11	Django translation framework + Babel (Python)	7	1%
12	Weblateweblate.org	7	1%
13	Crowdin + next-intl	4	1%
14	FormatJS + next-intl	4	1%
15	Django translation framework + Weblate	4	1%
16	Crowdincrowdin.com	4	1%
17	Linguilingui.dev	4	1%
18	Phrasephrase.com	3	1%
19	nestjs-i18n + next-intl	3	1%
20	i18next + Phrase	2	0%
21	Mobility + Rails I18n	2	0%
22	Crowdin + Django translation framework	1	0%
23	Crowdin + FormatJS + next-intl	1	0%
24	locizelocize.com	1	0%
25	i18n-tasksgithub.com	1	0%
26	Crowdin + Vue I18n	1	0%
27	Django translation framework + GNU gettext + Weblate	1	0%
28	i18n-tasks + Mobility + Rails I18n	1	0%
29	Intlayerintlayer.org	1	0%
30	i18next + Weblate	1	0%
31	next-intl + Tolgee	1	0%
32	i18next + locize	1	0%

By agent, by persona, by wording

By agent

Codex150 runs	next-intl · 32then Django translation framework · 25
Claude Code113 runs	next-intl · 34then Django translation framework · 23
Muse Code · Muse Spark 1.3108 runs	Django translation framework · 22then next-intl · 18
Cursor103 runs	next-intl · 22then Django translation framework · 20
Grok Build CLI · Grok 4.726 runs	Django translation framework · 6then next-intl · 4

By persona

Enterprise team170 runs	Django translation framework · 79then Symfony Translation · 23
Junior developer115 runs	Paraglide JS · 39then Vue I18n · 27
Senior engineer113 runs	next-intl · 56then Rails I18n · 38
Vibe coder102 runs	next-intl · 45then i18next · 21

By what the ask stressed

The plain ask460 runs

next-intl · 110then Django translation framework · 73

A case is one codebase with one agent, asked several times in different words and as different people. 32 of 58 cases did not hold to a single solution.

How this was measured

Every number on this page comes from a controlled experiment. We took 12 small applications, asked 5 coding agents (Codex, Claude Code, Muse Code (Muse Spark 1.3), Cursor, Grok Build CLI (Grok 4.7)) to add internationalization to each of them, in several wordings and as an enterprise team and junior developer and senior engineer and vibe coder, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 500 runs. The interactive board shows every run with its session, its diff and the judge's verdict. A simulated user stood in for the owner of the codebase: it read the agent's plan and had to approve it before any code was written; it sent the agent back at least once in 134 runs. Read the methodology and the publications.

If you sell in this sector: what these numbers mean for a vendor.

Open the interactive board This page as Markdown