CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915981296664576 |
|---|---|
| author | Xu, Zhipeng Ji, Junhao Chen, Zulong Liu, Zhenghao Liu, Qing Peng, Chunyi Qin, Zubao Xu, Ze Wan, Jianqiang Tang, Jun Yang, Zhibo Bai, Shuai Liu, Dayiheng |
| author_facet | Xu, Zhipeng Ji, Junhao Chen, Zulong Liu, Zhenghao Liu, Qing Peng, Chunyi Qin, Zubao Xu, Ze Wan, Jianqiang Tang, Jun Yang, Zhibo Bai, Shuai Liu, Dayiheng |
| contents | Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-world applications remains underexplored, as existing benchmarks adopt task scopes misaligned with practical applications and assume homogeneous acquisition conditions. To address this gap, we introduce CC-OCR V2, a comprehensive and challenging OCR benchmark tailored to real-world document processing. CC-OCR V2 focuses on practical enterprise document processing tasks and incorporates hard and corner cases that are critical yet underrepresented in prior benchmarks, covering 5 major OCR-centric tracks: text recognition, document parsing, document grounding, key information extraction, and document question answering, comprising 7,093 high-difficulty samples. Extensive experiments on 14 advanced LMMs reveal that current models fall short of real-world application requirements. Even state-of-the-art LMMs exhibit substantial performance degradation across diverse tasks and scenarios. These findings reveal a significant gap between performance on current benchmarks and effectiveness in real-world applications. We release the full dataset and evaluation toolkit at https://github.com/eioss/CC-OCR-V2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing Xu, Zhipeng Ji, Junhao Chen, Zulong Liu, Zhenghao Liu, Qing Peng, Chunyi Qin, Zubao Xu, Ze Wan, Jianqiang Tang, Jun Yang, Zhibo Bai, Shuai Liu, Dayiheng Computation and Language Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-world applications remains underexplored, as existing benchmarks adopt task scopes misaligned with practical applications and assume homogeneous acquisition conditions. To address this gap, we introduce CC-OCR V2, a comprehensive and challenging OCR benchmark tailored to real-world document processing. CC-OCR V2 focuses on practical enterprise document processing tasks and incorporates hard and corner cases that are critical yet underrepresented in prior benchmarks, covering 5 major OCR-centric tracks: text recognition, document parsing, document grounding, key information extraction, and document question answering, comprising 7,093 high-difficulty samples. Extensive experiments on 14 advanced LMMs reveal that current models fall short of real-world application requirements. Even state-of-the-art LMMs exhibit substantial performance degradation across diverse tasks and scenarios. These findings reveal a significant gap between performance on current benchmarks and effectiveness in real-world applications. We release the full dataset and evaluation toolkit at https://github.com/eioss/CC-OCR-V2. |
| title | CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.03903 |