Do coding agents recommend Amazon Textract?
Amazon Textract was chosen in 13% of 801 judged document processing sessions, ranking third.
Amazon Textract was chosen in 13% of 801 judged document processing sessions, ranking third. It was also raised as a candidate in 214 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 Amazon Textract. What an agent actually installed.
The numbers
| Category | Document processing |
| Sessions in the category | 801 |
| Sessions where Amazon Textract was chosen | 103 |
| Install share | 13% |
| Rank in category | 3 of 42 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 214 |
| Chosen when considered | 32% |
| Site | aws.amazon.com |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 11 points of each other on Amazon Textract, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Amazon Textract | Share |
|---|---|---|---|
| Claude Code | 180 | 11 | 6% |
| Codex | 235 | 41 | 17% |
| Cursor | 180 | 20 | 11% |
| Grok Build CLI | 30 | 3 | 10% |
| Muse Code | 176 | 28 | 16% |
By who was asking
Amazon Textract does much better with one kind of buyer than another. It won 30% of sessions asked as enterprise team and 3% of those asked as vibe coder.
| Who is asking | Sessions | Chose Amazon Textract | Share |
|---|---|---|---|
| Vibe coder | 68 | 2 | 3% |
| Junior developer | 327 | 34 | 10% |
| Senior engineer | 270 | 26 | 10% |
| Enterprise team | 136 | 41 | 30% |
What Amazon Textract 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 | 150 | 19% |
| 3 | Amazon Textract (this page) | 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
Amazon Textract was raised in 214 sessions and chosen in 103. 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 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 Amazon Textract: 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 Amazon Textract?
Yes. Amazon Textract was chosen in 103 of the 801 judged sessions in document processing, a 13% install share, ranking third in its category.
Does Claude Code recommend Amazon Textract?
In 11 of the 180 sessions in document processing run with Claude Code, which is 6%.
Do different coding agents treat Amazon Textract differently?
Yes, and by a wide margin. Codex chose it in 17% of its runs and Claude Code in 6%.
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 Amazon Textract considered but not chosen?
It was raised as a candidate in 214 sessions without being chosen, and chosen in 103. That is a 32% 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.