Do coding agents recommend Ocrolus?
Ocrolus was chosen in 4% of 360 judged document processing sessions, ranking sixth. Measured with Claude Code, Codex and Cursor.
Ocrolus was chosen in 4% of 360 judged document processing sessions, ranking sixth. It was also raised as a candidate in 29 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in document processing inside a realistic codebase. Not what a chat assistant says about Ocrolus. What an agent actually installed.
One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about document processing in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Document processing |
| Sessions in the category | 360 |
| Sessions where Ocrolus was chosen | 15 |
| Install share | 4% |
| Rank in category | 6 of 30 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 29 |
| Chosen when considered | 34% |
| Site | ocrolus.com |
By agent
With 15 wins spread across three 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.
| Agent | Sessions | Chose Ocrolus | Share |
|---|---|---|---|
| Claude Code | 120 | 0 | 0% |
| Codex | 120 | 8 | 7% |
| Cursor | 120 | 7 | 6% |
By who was asking
Ocrolus does much better with one kind of buyer than another. It won 50% of sessions asked as enterprise team and 0% of those asked as senior engineer.
| Who is asking | Sessions | Chose Ocrolus | Share |
|---|---|---|---|
| Vibe coder | 30 | 0 | 0% |
| Junior developer | 180 | 0 | 0% |
| Senior engineer | 120 | 0 | 0% |
| Enterprise team | 30 | 15 | 50% |
What Ocrolus was up against
The full ranking in document processing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Anthropic Claude | 87 | 24% |
| 2 | Azure AI Document Intelligence | 76 | 21% |
| 3 | Amazon Textract | 37 | 10% |
| 4 | Google Cloud Document AI | 31 | 9% |
| 5 | Google Gemini | 17 | 5% |
| 6 | Ocrolus (this page) | 15 | 4% |
| 7 | Reducto | 13 | 4% |
| 8 | Azure AI Content Understanding | 11 | 3% |
What this means
Ocrolus was raised in 29 sessions and chosen in 15. 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 360 sessions in document processing are part of a published set of 7,385, 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 Ocrolus: 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 Ocrolus?
Yes. Ocrolus was chosen in 15 of the 360 judged sessions in document processing, a 4% install share, ranking sixth in its category.
Does Claude Code recommend Ocrolus?
In 0 of the 120 sessions in document processing run with Claude Code, which is 0%.
Do different coding agents treat Ocrolus differently?
Not much. The three agents chose it at similar rates, between 0% and 7% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 84 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 Ocrolus considered but not chosen?
It was raised as a candidate in 29 sessions without being chosen, and chosen in 15. That is a 34% conversion from considered to chosen.
Where this comes from
Armature ran 7,385 judged sessions with Claude Code, Codex and Cursor inside 84 realistic codebases, and published every run. The numbers on this page come from that work.