Tools,

Best open source OCR, tested on 10 book pages

1,954 of 1,955

words, olmOCR-2 and LightOnOCR-2 1B

Pick an engine

The top 10 are all vision models

10 scanned book pages, of 1,955 words
Engine Words Time
olmOCR-2 7B 1,954 77 s
LightOnOCR-2 1B 1,954 72 s
LightOnOCR-3 1,953 130 s
Unlimited-OCR 1,951 297 s
Qwen3-VL 8B 1,951 139 s
GLM-OCR 1,950 118 s
Gemma 4 e4b (Ollama) 1,950 32 s
MinerU 4.2.1 1,949 41 s
DeepSeek-OCR 2 1,948 83 s
PaddleOCR-VL 1.6 1,947 73 s

The best classic engine, PaddleOCR, found 1,919 on a CPU. Tesseract found 1,878 in 31 s.

Times are rough. Most include the model load. Some ran on the Mac GPU, some on the CPU, on different days.

Pick by what you have

You have Pick Words
A GPU (I tested a Mac) LightOnOCR-2 1B 1,954
Ollama and one command Gemma 4 e4b 1,950
A CPU and Python PaddleOCR 3.7 1,919
A CPU and half a minute Tesseract 5.5.4 1,878
Node.js Scribe.js (AGPL-3.0) 1,895
A scanned PDF to search OCRmyPDF (Tesseract inside) 1,855

LightOnOCR-2 has 1B parameters, a seventh of olmOCR-2's 7B. Each link goes to its own test, with the command and the traps.

All 28 engines, same pages

16 vision language models and 12 classic engines. Each row is the run its own page leads with. tesseract.js shares the Scribe.js page, and Tesseract is tonight's rerun.

16 vision language models
Engine Words Time
olmOCR-2 7B 1,954 77 s
LightOnOCR-2 1B 1,954 72 s
LightOnOCR-3 1,953 130 s
Unlimited-OCR 1,951 297 s
Qwen3-VL 8B 1,951 139 s
GLM-OCR 1,950 118 s
Gemma 4 e4b (Ollama) 1,950 32 s
MinerU 4.2.1 1,949 41 s
DeepSeek-OCR 2 1,948 83 s
PaddleOCR-VL 1.6 1,947 73 s
dots.ocr 1,946 168 s
GOT-OCR 2.0 1,936 134 s
Surya 1,926 56 s
Chandra 2 1,911 169 s
Granite-Docling 258M 1,897 54 s
Florence-2 1,887 158 s
12 classic engines
Engine Words Time
PaddleOCR 3.7 (PP-OCRv6) 1,919 319 s
Scribe.js 0.18.2 1,895 15 s
RapidOCR 3.10.0 1,894 55 s
Tesseract 5.5.4 1,878 31 s
tesseract.js 7.0.0 1,876 18 s
Kraken 7.1.1 1,875 380 s
docTR 1,869 13 s
Pix2Text 1.1.7 1,810 99 s
ocrs 0.14.0 (Rust) 1,743 35 s
EasyOCR 1.7.2 1,658 58 s
OpenCV 5.0.0 (EAST + CRNN) 1,533 283 s
keras-ocr 0.9.3 1,334 870 s
Settings behind four rows
  • PaddleOCR: the page's --fast setup. The default read 1,908.
  • GOT-OCR 2.0: format mode. Plain mode read 1,591.
  • Qwen3-VL: temperature 0. The Ollama default read 1,950.
  • PaddleOCR-VL: the GGUF in llama-server, not the CPU path of the model card.

Six licenses with a catch

dots.ocr has its own model agreement, which allows business use. The other 21 are Apache-2.0 or MIT, two with Creative Commons models.

Same pages, same scorer

Every engine read the same 10 proofread book pages from Wikisource, 1,955 words in all. One script scores every run: true words found, in order, with exact case and punctuation (curly quotes and dashes count as plain ones).

How I know the old runs match
  • Most runs read a PDF of the 10 page images from Nov 10. A reboot on Nov 14 deleted it, so the later runs used a rebuilt copy.
  • Both PDFs keep the JPEG bytes as they are, at a 300 dpi page size. The image hashes from Nov 11 match today's.
  • Tonight RapidOCR read today's PDF and gave the same text, byte for byte, as its Nov 13 run on the Nov 10 PDF. Three runs from earlier today also matched byte for byte:
Rerun Then Tonight
RapidOCR, from the Nov 10 PDF 1,894 1,894
Unlimited-OCR in llama.cpp 1,949 1,949
Tesseract 5.5.4 1,878 1,878
The Actor's code 1,879 1,879

The vision models, docTR, Kraken and EasyOCR ran on the GPU of one Apple Silicon Mac. The other classic engines ran on the CPU, most on 2 threads. Every run had low priority.

What 10 pages cannot tell you

Scanned pages to text, no GPU

Run it yourself. Our Apify Actor reads PDF, PNG, JPEG, WEBP and TIFF for $0.006 a page, with no model files. Its code found 1,879 of these 1,955 words.

Try the Actor

Or send us the scan. Tack, our AI, does the job for $29, up to 50 pages. First page free.

Get one page free

Questions people ask

What is the best open source OCR in 2026?

On 10 scanned English book pages, olmOCR-2 7B and LightOnOCR-2 1B found 1,954 of 1,955 words. Both are Apache-2.0 vision models. olmOCR-2's card adds a research and education note. On a CPU, PaddleOCR found 1,919.

What is the best open source OCR for PDF files?

To make a scanned PDF searchable, OCRmyPDF found 1,855 of 1,955 words with Tesseract inside. To get the text out, the olmOCR toolkit takes the PDF itself and found 1,954.

Is Tesseract still good enough?

For clean printed pages, often yes. Tesseract 5.5.4 found 1,878 of 1,955 words in 31 s on a CPU. The two best vision models found 76 more words.

What is the best open source OCR for handwriting?

This test has no handwriting. Our TrOCR and Tesseract handwriting pages test 100 handwritten notes.