From the experiment

Do coding agents recommend Arctic?

Arctic was chosen in 2% of 520 judged authentication sessions, ranking seventh. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.

Published September 23, 2026 Read as Markdown

Arctic was chosen in 2% of 520 judged authentication sessions, ranking seventh. It was also raised as a candidate in 21 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 authentication inside a realistic codebase. Not what a chat assistant says about Arctic. What an agent actually installed.

The numbers

CategoryAuthentication
Sessions in the category520
Sessions where Arctic was chosen9
Install share2%
Rank in category7 of 26
Codebases it won in2
Raised as a candidate, not chosen21
Chosen when considered30%
Sitearcticjs.dev

By agent

With 9 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose ArcticShare
Claude Code13354%
Codex13600%
Cursor13311%
Grok Build CLI5024%
Muse Code6811%

By who was asking

Arctic performs similarly across the four kinds of buyer, from 0% to 13%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.

Who is askingSessionsChose ArcticShare
Vibe coder71913%
Junior developer16000%
Senior engineer17400%
Enterprise team11500%

What Arctic was up against

The full ranking in authentication, from the same sessions:

#ProductRuns wonShare
1Auth011723%
2WorkOS AuthKit11723%
3Clerk6112%
4Microsoft Entra ID5511%
5Built in-house (no product adopted)489%
6Better Auth214%
7Keycloak133%
8Arctic (this page)92%

What this means

Arctic was raised in 21 sessions and chosen in 9. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

Where these numbers come from

The 520 sessions in authentication are part of a published set of 11,878, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every authentication run can be replayed on the board.

If you work on Arctic: 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 Arctic?

Yes. Arctic was chosen in 9 of the 520 judged sessions in authentication, a 2% install share, ranking seventh in its category.

Does Claude Code recommend Arctic?

In 5 of the 133 sessions in authentication run with Claude Code, which is 4%.

Do different coding agents treat Arctic differently?

Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 4% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 91 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 Arctic considered but not chosen?

It was raised as a candidate in 21 sessions without being chosen, and chosen in 9. That is a 30% conversion from considered to chosen.

Where this comes from

Armature ran 11,878 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages