Do coding agents recommend Reducto?
Reducto was chosen in 2% of 801 judged document processing sessions, ranking ninth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Reducto was chosen in 2% of 801 judged document processing sessions, ranking ninth. It was also raised as a candidate in 185 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 Reducto. What an agent actually installed.
The numbers
| Category | Document processing |
| Sessions in the category | 801 |
| Sessions where Reducto was chosen | 20 |
| Install share | 2% |
| Rank in category | 9 of 42 |
| Codebases it won in | 6 |
| Raised as a candidate, not chosen | 185 |
| Chosen when considered | 10% |
| Site | reducto.ai |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 6 points of each other on Reducto, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Reducto | Share |
|---|---|---|---|
| Claude Code | 180 | 3 | 2% |
| Codex | 235 | 7 | 3% |
| Cursor | 180 | 10 | 6% |
| Grok Build CLI | 30 | 0 | 0% |
| Muse Code | 176 | 0 | 0% |
By who was asking
Reducto performs similarly across the four kinds of buyer, from 0% to 5%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Reducto | Share |
|---|---|---|---|
| Vibe coder | 68 | 0 | 0% |
| Junior developer | 327 | 7 | 2% |
| Senior engineer | 270 | 13 | 5% |
| Enterprise team | 136 | 0 | 0% |
What Reducto 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 | 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
This is an integration problem, not a presence problem. Agents raised Reducto in 185 sessions and chose it in 20, 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 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 Reducto: 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 Reducto?
Yes. Reducto was chosen in 20 of the 801 judged sessions in document processing, a 2% install share, ranking ninth in its category.
Does Claude Code recommend Reducto?
In 3 of the 180 sessions in document processing run with Claude Code, which is 2%.
Do different coding agents treat Reducto differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 6% 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 Reducto considered but not chosen?
It was raised as a candidate in 185 sessions without being chosen, and chosen in 20. That is a 10% 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.