OpenCodePapers

optical-character-recognition-ocr-on-videodb

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.
PaperCodeAverage AccuracyCharacter Error Rate (CER)Word Error Rate (WER)ModelNameReleaseDate
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments✓ Link76.220.23780.5117GPT-4o2025-02-10
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments✓ Link76.130.23870.2385Gemini-1.5 Pro2025-02-10
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments✓ Link67.710.32290.4663Claude-3 Sonnet2025-02-10
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments✓ Link56.980.76200.4302RapidOCR2025-02-10
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments✓ Link49.300.50700.8262EasyOCR2025-02-10
Check out how to contribute new results.