chandra ocr 2

---
library_name: transformers
license: openrail
license_link: LICENSE
tags:
- ocr
- pdf
- markdown
- layout
---

<p align="center">
<img src="datalab-logo.png" alt="Datalab Logo" width="150"/>
</p>

Chandra OCR 2

Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.

Try Chandra in the free playground, or use the hosted API for higher accuracy and speed.

What's New in Chandra 2

• 85.8% olmocr bench score (sota), 77.8% multilingual bench score (12% improvement over Chandra 1)

• Significant improvements to math, tables, complex layouts

• Improved layout, especially on wider documents

• Significantly better image captioning

• 90+ language support with major accuracy gains

Features

• Convert documents to markdown, HTML, or JSON with detailed layout information

• Excellent handwriting support

• Reconstructs forms accurately, including checkboxes

• Strong performance with tables, math, and complex layouts

• Extracts images and diagrams, with captions and structured data

• Support for 90+ languages

<img src="handwritten_form.png" width="600px"/>

Quickstart

pip install chandra-ocr
With vLLM (recommended, easy install)
chandra_vllm
chandra input.pdf ./output
With HuggingFace (requires torch)
pip install chandra-ocr[hf]
chandra input.pdf ./output --method hf

Usage

With vLLM (recommended)

from chandra.model import InferenceManager
from chandra.model.schema import BatchInputItem
from PIL import Image
Start vLLM server first with: chandra_vllm
manager = InferenceManager(method="vllm")
batch = [
    BatchInputItem(
        image=Image.open("document.png"),
        prompt_type="ocr_layout"
    )
]
result = manager.generate(batch)[0]
print(result.markdown)

With HuggingFace Transformers

from transformers import AutoModelForImageTextToText, AutoProcessor
from chandra.model.hf import generate_hf
from chandra.model.schema import BatchInputItem
from chandra.output import parse_markdown
from PIL import Image
import torch
model = AutoModelForImageTextToText.from_pretrained(
    "datalab-to/chandra-ocr-2",
    dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()
model.processor = AutoProcessor.from_pretrained("datalab-to/chandra-ocr-2")
model.processor.tokenizer.padding_side = "left"
batch = [
    BatchInputItem(
        image=Image.open("document.png"),
        prompt_type="ocr_layout"
    )
]
result = generate_hf(batch, model)[0]
markdown = parse_markdown(result.raw)
print(markdown)

Benchmarks

olmOCR Benchmark

<img src="bench.png" width="600px"/>

| Model | ArXiv | Old Scans Math | Tables | Old Scans | Headers and Footers | Multi column | Long tiny text | Base | Overall | Source |
|:----------|:--------:|:--------------:|:--------:|:---------:|:-------------------:|:------------:|:--------------:|:----:|:--------------:|:------:|
| Datalab API | 90.4 | 90.2 | 90.7 | 54.6 | 91.6 | 83.7 | 92.3 | 99.9 | 86.7 ± 0.8 | Own benchmarks |
| Chandra 2 | 86.9 | 89.1 | 92.1 | 51.1 | 91.4 | 82.1 | 93.7 | 99.9 | 85.8 ± 0.8 | Own benchmarks |
| dots.ocr 1.5 | 85.9 | 85.5 | 90.7 | 48.2 | 94.0 | 85.3 | 81.6 | 99.7 | 83.9 | dots.ocr repo |
| Chandra 1 | 82.2 | 80.3 | 88.0 | 50.4 | 90.8 | 81.2 | 92.3 | 99.9 | 83.1 ± 0.9 | Own benchmarks |
| olmOCR 2 | 83.0 | 82.3 | 84.9 | 47.7 | 96.1 | 83.7 | 81.9 | 99.6 | 82.4 | olmocr repo |
| dots.ocr | 82.1 | 64.2 | 88.3 | 40.9 | 94.1 | 82.4 | 81.2 | 99.5 | 79.1 ± 1.0 | dots.ocr repo |
| olmOCR v0.3.0 | 78.6 | 79.9 | 72.9 | 43.9 | 95.1 | 77.3 | 81.2 | 98.9 | 78.5 ± 1.1 | olmocr repo |
| Datalab Marker v1.10.0 | 83.8 | 69.7 | 74.8 | 32.3 | 86.6 | 79.4 | 85.7 | 99.6 | 76.5 ± 1.0 | Own benchmarks |
| Deepseek OCR | 75.2 | 72.3 | 79.7 | 33.3 | 96.1 | 66.7 | 80.1 | 99.7 | 75.4 ± 1.0 | Own benchmarks |
| Mistral OCR API | 77.2 | 67.5 | 60.6 | 29.3 | 93.6 | 71.3 | 77.1 | 99.4 | 72.0 ± 1.1 | olmocr repo |
| GPT-4o (Anchored) | 53.5 | 74.5 | 70.0 | 40.7 | 93.8 | 69.3 | 60.6 | 96.8 | 69.9 ± 1.1 | olmocr repo |
| Qwen 3 VL 8B | 70.2 | 75.1 | 45.6 | 37.5 | 89.1 | 62.1 | 43.0 | 94.3 | 64.6 ± 1.1 | Own benchmarks |
| Gemini Flash 2 (Anchored) | 54.5 | 56.1 | 72.1 | 34.2 | 64.7 | 61.5 | 71.5 | 95.6 | 63.8 ± 1.2 | olmocr repo |

Examples

| Type | Name | Link |
|------|------|------|
| Tables | Statistical Distribution | View |
| Tables | Financial Table | View |
| Forms | Registration Form | View |
| Forms | Lease Form | View |
| Math | CS229 Textbook | View |
| Math | Handwritten Math | View |
| Math | Chinese Math | View |
| Handwriting | Cursive Writing | View |
| Handwriting | Handwritten Notes | View |
| Languages | Arabic | View |
| Languages | Japanese | View |
| Languages | Hindi | View |
| Languages | Russian | View |
| Other | Charts | View |
| Other | Chemistry | View |

Multilingual Benchmark (43 Languages)

The table below covers the 43 most common languages, benchmarked across multiple models. For a comprehensive evaluation across 90 languages (Chandra 2 vs Gemini 2.5 Flash only), see the full 90-language benchmark.

<img src="multilingual.png" width="600px"/>

| Language | Datalab API | Chandra 2 | Chandra 1 | Gemini 2.5 Flash | GPT-5 Mini |
|---|:---:|:---:|:---:|:---:|:---:|
| ar | 67.6% | 68.4% | 34.0% | 84.4% | 55.6% |
| bn | 85.1% | 72.8% | 45.6% | 55.3% | 23.3% |
| ca | 88.7% | 85.1% | 84.2% | 88.0% | 78.5% |
| cs | 88.2% | 85.3% | 84.7% | 79.1% | 78.8% |
| da | 90.1% | 91.1% | 88.4% | 86.0% | 87.7% |
| de | 93.8% | 94.8% | 83.0% | 88.3% | 93.8% |
|