Back to News
BaiduJanuary 29, 2026

PaddleOCR-VL-1.5

Open Source
OCR

Explore PaddleOCR-VL-1.5

Visit the official website to learn more and get started

### TL;DR

PaddleOCR-VL-1.5 is an advanced model in the PaddleOCR-VL series, achieving a state-of-the-art accuracy of 94.5% on OmniDocBench v1.5. It introduces robust document parsing capabilities, including support for irregular-shaped localization and text spotting tasks.

Key Insights & Metrics

Pricing
Free
Cost structure
Version
1.5
Current release version
Hardware
Compatible with AMD Instinct™ MI Series GPUs using the AMD ROCm™ software release 7.0
Compute requirements
Category
Open Source
Licensing model
Region
China
Primary region

Key Features

  • 94.5% accuracy on OmniDocBench v1.5
  • Supports irregular-shaped localization for skewed and warped documents
  • Includes text spotting and seal recognition tasks
  • Compact 0.9B parameter size for high efficiency
  • Enhanced performance in real-world scenarios like scanning and illumination changes

Discussion

0
Upvotes
0
Downvotes
0 reviews

Sign in to leave a review

Reviews

No reviews yet. Be the first to review!

🚀 Join the AI dev community — follow us everywhere

© 2026 MARKTECHPOST AI MEDIA INC. All rights reserved.Terms & ConditionsPrivacy Policy
Beta Mode