CC-OCR

Name: CC-OCR Benchmark Results
Creator: South China University of Technology
License: https://creativecommons.org/licenses/by/4.0/

South China University of Technology

Multi-scene text reading, key information extraction, multilingual text, and document parsing benchmark.

Models5

Papers12

Metrics4

SOTA History

Coming Soon

Visual timeline of state-of-the-art progression over time will appear here.

F1 score on multi-scene text reading

Higher is better

Rank	Model	Code	Score	Paper / Source
1	gemini-15-pro Multi-Scene Text Reading - Overall F1 score	-	83.25%	AlphaXiv
2	qwen2-vl-72b	HF	77.95%	AlphaXiv
3	internvl2-76b	-	76.92%	AlphaXiv
4	gpt-4o	-	76.4%	AlphaXiv
5	claude-35-sonnet	-	72.87%	AlphaXiv

F1 score on key information extraction

Higher is better

Rank	Model	Code	Score	Paper / Source
1	qwen2-vl-72b Key Information Extraction - Overall F1 score	HF	71.76%	AlphaXiv
2	gemini-15-pro	-	67.28%	AlphaXiv
3	claude-35-sonnet	-	64.58%	AlphaXiv
4	gpt-4o	-	63.45%	AlphaXiv

F1 score on multilingual text (10 languages)

Higher is better

Rank	Model	Code	Score	Paper / Source
1	gemini-15-pro Multilingual Text Reading - 10 languages	-	78.97%	AlphaXiv
2	gpt-4o	-	73.44%	AlphaXiv

Average score on document parsing

Higher is better

Rank	Model	Code	Score	Paper / Source
1	gemini-15-pro Document Parsing - Average Score	-	62.37	AlphaXiv