Do coding agents recommend Anthropic Claude?
Anthropic Claude was chosen in 19% of 801 judged document processing sessions, ranking second.
Anthropic Claude was chosen in 19% of 801 judged document processing sessions, ranking second. It was also raised as a candidate in 169 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 document processing inside a realistic codebase. Not what a chat assistant says about Anthropic Claude. What an agent actually installed.
The numbers
| Category | Document processing |
| Sessions in the category | 801 |
| Sessions where Anthropic Claude was chosen | 150 |
| Install share | 19% |
| Rank in category | 2 of 42 |
| Codebases it won in | 11 |
| Raised as a candidate, not chosen | 169 |
| Chosen when considered | 47% |
| Site | anthropic.com |
By agent
The agents treat Anthropic Claude very differently. Claude Code chose it in 62% of its sessions in this category and Codex in 0%, a spread of 62 points.
| Agent | Sessions | Chose Anthropic Claude | Share |
|---|---|---|---|
| Claude Code | 180 | 112 | 62% |
| Codex | 235 | 0 | 0% |
| Cursor | 180 | 17 | 9% |
| Grok Build CLI | 30 | 1 | 3% |
| Muse Code | 176 | 20 | 11% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 0%, not 19%.
By who was asking
Anthropic Claude does much better with one kind of buyer than another. It won 26% of sessions asked as junior developer and 4% of those asked as enterprise team.
| Who is asking | Sessions | Chose Anthropic Claude | Share |
|---|---|---|---|
| Vibe coder | 68 | 16 | 24% |
| Junior developer | 327 | 84 | 26% |
| Senior engineer | 270 | 45 | 17% |
| Enterprise team | 136 | 5 | 4% |
What Anthropic Claude was up against
The full ranking in document processing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Azure AI Document Intelligence | 193 | 24% |
| 2 | Anthropic Claude (this page) | 150 | 19% |
| 3 | Amazon Textract | 103 | 13% |
| 4 | Google Cloud Document AI | 49 | 6% |
| 5 | OpenAI models | 46 | 6% |
| 6 | Google Gemini | 45 | 6% |
| 7 | Docling | 24 | 3% |
| 8 | Apache PDFBox | 23 | 3% |
What this means
A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.
The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.
Where these numbers come from
The 801 sessions in document processing 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 document processing run can be replayed on the board.
If you work on Anthropic Claude: 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 Anthropic Claude?
Yes. Anthropic Claude was chosen in 150 of the 801 judged sessions in document processing, a 19% install share, ranking second in its category.
Does Claude Code recommend Anthropic Claude?
In 112 of the 180 sessions in document processing run with Claude Code, which is 62%.
Do different coding agents treat Anthropic Claude differently?
Yes, and by a wide margin. Claude Code chose it in 62% of its runs and Codex in 0%.
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 Anthropic Claude considered but not chosen?
It was raised as a candidate in 169 sessions without being chosen, and chosen in 150. That is a 47% 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.