[Models](/models)/[Text Extraction](/models?category=text_extraction)/allenai/olmOCR-2-7B-1025

HFOCRapache-2.0

# olmOCR-2-7B-1025

by allenai

Document OCR with a published per-category score, including the categories that usually go unreported

88Kdl/month

158likes

8.3Bparams

[HuggingFace](https://huggingface.co/allenai/olmOCR-2-7B-1025)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`allenai/olmOCR-2-7B-1025`

## Deploy olmOCR-2-7B-1025

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

OCR benchmarks tend to report one number over clean documents, which tells you nothing about the pages that break pipelines. olmOCR-2 publishes a score per category on olmOCR-bench, and the interesting row is the low one: 48.3 on old scans, against 99.7 on clean base documents and 95.7 on headers and footers. That spread is the real shape of document OCR, and a model that shows it lets you decide whether your corpus is the easy kind.

It is a Qwen2.5-VL-7B-Instruct fine-tune trained on the olmOCR-mix-1025 dataset and then tuned further with GRPO reinforcement learning aimed at equations, tables and awkward cases. Unlike a classic OCR engine it reads a page the way a vision-language model does, which is what lets it recover reading order in multi-column layouts and keep table structure intact instead of flattening cells into a line.

## Architecture

A vision-language model rather than a detector plus recogniser: Qwen2.5-VL-7B-Instruct fine-tuned on olmOCR-mix-1025, then further tuned with GRPO reinforcement learning on math equations, tables and difficult scans. It takes one document image per call, rendered so the longest dimension is 1,288 pixels, plus page metadata in the prompt. 8.3B parameters in BF16; an FP8 build is the recommended one for inference.

## Mixpeek SDK Integration

IngestRetrieve

\# Render the page so its longest side is 1288px before you send it. The
# toolkit does this for you and also handles rotation and retries.
from olmocr.pipeline import run\_page
from mixpeek import Mixpeek

mx = Mixpeek(api\_key="API\_KEY")
page\_text = run\_page("archive/1987-annual-report.pdf", page\_num=12)

mx.namespaces.documents.upsert(
    namespace\_id="ns\_your\_namespace",
    documents=\[{
        "document\_id": "annual-1987-page-12",
        "payload": {
            "source\_key": "archive/1987-annual-report.pdf#page=12",
            "text": page\_text,
        },
    }\],
)

## Capabilities

*   Per-category published accuracy on olmOCR-bench rather than a single headline number
*   Reading-order recovery in multi-column layouts (84.3 on the multi-column category)
*   Table structure preserved instead of flattened (84.3 on tables)
*   Math equations handled as a trained target (82.1 on old scans math)
*   Batch inference at scale through the olmOCR toolkit on vLLM

## Use Cases on Mixpeek

Digitising archives of scanned reports where layout carries meaning

Extracting tables from filings and statements for downstream structuring

Preparing document text for retrieval when a classic OCR engine loses the layout

Anything where you need to know the error rate on bad scans before you commit

## Benchmarks

Dataset

Metric

Score

Source

olmOCR-bench

Overall

82.3 +/- 1.1

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

Base documents

99.7

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

Headers and footers

95.7

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

Tables

84.3

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

Multi column

84.3

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

ArXiv

82.9

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

Old scans math

82.1

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

Long tiny text

81.4

Allen AI model card, olmOCR pipeline v0.4.0

olmOCR-bench

Old scans

48.3

Allen AI model card, olmOCR pipeline v0.4.0

## Frequently Asked Questions

### Why is the old-scans score so much lower than the rest?

Degraded scans are harder: bleed-through, skew, speckle and broken glyphs remove the evidence any model needs. 48.3 on that category against 99.7 on clean pages is the honest spread, and it is the number to plan around if your archive is microfilm or photocopies. Pre-processing the images helps more than swapping models at that end of the range.

### Should I use the BF16 weights or the FP8 build?

FP8 for inference. The card recommends it for everything except further fine-tuning, and the published scores differ by a tenth of a point, which is inside the reported error bar.

### Is a 7B vision-language model overkill compared with a classic OCR engine?

For clean single-column text, yes, and a traditional engine is far cheaper per page. The case for this model is the pages where layout carries meaning: multi-column articles, tables, equations. A common arrangement is a cheap engine by default with this one routed the difficult pages.

### Does Mixpeek run this model?

Not as a managed extractor. Run the olmOCR toolkit over your PDFs and upsert the text, or use a managed document extractor when the corpus does not need this level of layout recovery.

## Explore on Mixpeek

[

More Text Extraction models

Compare alternatives in this category

](/models?category=text_extraction)[

Best Document AI Platforms

Hand-picked tools & platforms compared

](/curated-lists/best-document-ai-platforms)[

OCR & Document AI Internals

Deep-dive technical guide

](/guides/ocr-document-ai-internals)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

FrameworkHF

Organizationallenai

FeatureOCR

Outputtext + bbox

Modalitiesvideo, image, document

RetrieverText-in-Image

Parameters8.3B

Licenseapache-2.0

Downloads/mo88K

Likes158

[

### Research Paper

olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

arxiv.org](https://olmocr.allenai.org/papers/olmocr.pdf)

### Build a pipeline with olmOCR-2-7B-1025

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

### Alternative Models

[

microsoft/trocr-large-printed

OCR

](/model/microsoft/trocr-large-printed)[

PaddlePaddle/paddleocr

OCR

](/model/PaddlePaddle/paddleocr)[

zai-org/GLM-OCR

OCR

](/model/zai-org/GLM-OCR)[

lightonai/LightOnOCR-2-1B

OCR

](/model/lightonai/LightOnOCR-2-1B)

### Related in Text Extraction

[

microsoft/codebert-base

Code Extraction

](/model/microsoft/codebert-base)[

Salesforce/codet5p-110m-embedding

Code Extraction

](/model/Salesforce/codet5p-110m-embedding)[

nomic-ai/nomic-embed-code

Code Extraction

](/model/nomic-ai/nomic-embed-code)[

Salesforce/SFR-Embedding-Code-2B\_R

Code Extraction

](/model/Salesforce/SFR-Embedding-Code-2B_R)