How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings

arXiv:2605.07492 · cs.CV · Submitted 2026-05-08 · Read on arXiv

cs.CV

Submitted: 2026-05-08

Updated: 2026-09-27

Code: https://github.com/Topdu/OpenOCR

Terminology

• Benchmark — 52× in this paper · explained in 2 episodes
• Robustness — 14× in this paper · explained in 5 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Failure Modes — 8× in this paper · explained in 3 episodes
• Decode — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Annotation Errors — 4× in this paper · explained in 1 episode
• Fidelity — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• alpha — 4× in this paper · explained in 1 episode
• Hallucination — 3× in this paper · explained in 3 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Error Taxonomy — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment Scores — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Parameter Efficiency — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Structural Integrity — 1× in this paper · explained in 3 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• Document AI: Benchmarks, Models and Applications
• PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
• GLM-OCR Technical Report
• MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
• Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting
• FireRed-OCR Technical Report
• HunyuanOCR Technical Report
• DeepSeek-OCR: Contexts Optical Compression
• DeepSeek-OCR 2: Visual Causal Flow
• Qwen3-VL Technical Report
• DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
• Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild
• MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios
• OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
• olmOCR 2: Unit Test Rewards for Document OCR
• OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
• Logics-Parsing-Omni Technical Report
• Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching
• Multimodal OCR: Parse Anything from Documents

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models