PaddleOCR Surpasses Tesseract to Become Top OCR Project on GitHub with 5 Million Parameters

AirdropBlackHole · 2026-03-30T14:29:31+00:00

Baidu's PaddleOCR has overtaken Tesseract to become the highest-rated OCR tool on GitHub, with 73,300 stars. Open-sourced in 2020, it supports over 100 languages and recently released PP-OCRv5, achieving high accuracy with fewer parameters.

AirdropBlackHole

2026-03-30 14:29:31

Abstract generation in progress

According to monitoring by 1M AI News, Baidu’s open-source OCR tool library PaddleOCR has surpassed Google’s long-standing OCR engine Tesseract with 73,300 stars on GitHub compared to Tesseract’s 73,200, making it the highest-rated OCR project on the platform. The third-ranked MinerU has 57,500 stars. PaddleOCR was open-sourced in 2020 and supports over 100 languages, covering more than 160 countries and regions. PaddleOCR has recently undergone intensive updates, with the release of PP-OCRv5 last week, which has only 5 million parameters and achieves accuracy comparable to that of billion-parameter visual language models on standard OCR benchmarks. Additionally, PaddleOCR-VL-1.5 set a new record with a 94.5% accuracy rate on the document parsing benchmark OmniDocBench v1.5.

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.

2 Likes