OpenCodePapers

optical-character-recognition-ocr-on-omnidocbench-v1-6

Optical Character Recognition (OCR)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents✓ Link96.87NaviDC-OCR2026-08-13
OvisOCR2 Technical Report96.58OvisOCR22026-07-15
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training✓ Link96.33PaddleOCR-VL-1.62026-06-02
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale✓ Link95.69MinerU2.5-Pro (1.2B)2026-04-06
WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing✓ Link95.38WeVisDoc-4B2026-09-17
HPD-Parsing: Hierarchical Parallel Document Parsing✓ Link94.91HPD-Parsing2026-07-21
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better✓ Link94.74HunyuanOCR-1.5 (1B)2026-07-06
Infinity-Parser2-Pro93.95Infinity-Parser2-Pro2026-05-11
Unlimited OCR Works✓ Link93.92Unlimited-OCR2026-06-22
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI✓ Link91.57MonkeyOCRv2-B-Parsing2026-07-13
Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards91.14Jina-OCR-v12026-09-02
Check out how to contribute new results. Then edit this file on GitLab or GitHub.