# LlamaIndex releases OCRia-1, a 4B document parsing model with a 37-page report

> Original title: We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing.

- Source: Jerry Liu
- Published: 2026-10-25T17:11:40.000Z
- Bad Influence: https://badinfluence.news/items/zas83v5hw3e2kuzu1kdi63yx7
- Original: https://x.com/jerryjliu0/status/2114404538652217370

## Summary

LlamaIndex releases OCRia-1, a 4B-parameter document parsing model, and publishes a 37-page technical report on it. The company says it leads ParseBench with a score of 87.4 and decodes 2x to 4x faster than recent open-weight models. The report compares OCRia-1 against Infinity-Parser, LightOnOCR 3, Chandra 2, and dots.mocr on olmOCR-bench, PulseBench-Tab, and fr-bench-pdf2md.

## Post

We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing.

✅ It contains comprehensive evals against most other major open-weight OCR models (e.g. Infinity-Parser, LightOnOCR 3, Chandra 2, dots.mocr) on multiple OCR benchmarks: ParseBench, olmOCR-bench, PulseBench-Tab, fr-bench-pdf2md.

✅ It contains detailed visibility into our data and training pipeline, to give a glimpse into how we’re able to curate the right document datasets to push the evaluation metrics within dimensions that matter for doc parsing.

✅ It is blazing fast ⚡️ decoding 2x-4x+ faster than the latest open-weight models.

✅ If you’re building your own vision models, there are 24 pages worth of appendix details (!!) that showcase all of our experimental findings from training to evals!

Check it out: https://www.llamaindex.ai/ocria/ocria-1-technical-report.pdf

Other links are in our blog! https://www.llamaindex.ai/blog/parse-ocria-1

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2114404413582282752%2Fimg%2FupvdHmJq5_nj66kr.jpg&mode=thumb&exp=1793923200&sig=1448e28266d6859b)

## Quoted post @jerryjliu0

> Today we’re releasing OCRia-1, a frontier VLM for document parsing that sets a new SOTA in accuracy, cost, and latency. 
> 
> It not only sets a new high score on ParseBench (87.4), but also leads in three 3rd-party benchmarks: olmOCR-bench* (83.5 overall, 92.9 on tables!), PulseBench-Tab (84.1), and fr-bench-pdf2md (72.1).
> 
> OCRia-1 is really, really good at parsing complex tables: nested headers, merged cells, irregular grids, scanned tables, and more. It is also fantastic at parsing complex unlabeled charts (line, bar, pie, technical diagrams), and preserving complex formatting. Most real-world enterprise documents contain at least one of the these, whether it’s a big tax withholding table or a public economic report.
> 
> It is a 4B model and outperforms all other models within a similar parameter class: LightOnOCR-3, Chandra-OCR 2, Mistral OCR 4.1, and more. It is also extremely fast.
> 
> All credit goes to our research team, who spent countless hours on curating a diverse dataset, tuning our training pipeline, and squeezing every last drop out of model optimization so that it can process billions of pages at scale. 
> 
> OCRia-1 as a base is powering all of our modes within LlamaParse (cost-effective, agentic, agentic plus), so you can access its capabilities today! 
> 
> If you’re processing millions/billions of documents at scale, we’re offering enterprises that book a demo up to $3k in credits for a guided evaluation.**
> 
> *olmOCR-bench scores are adjusted based on unifying rendering at 1,288px for all models 
> **enterprise POC credits apply to eligible organizations that book a demo

https://x.com/jerryjliu0/status/2113291928292790725