Home/Browse/Computer Vision/General OCR Capabilities/MME-VideoOCR

MME-VideoOCR

NTU

1,464 videos with 2,000 QA pairs across 25 tasks. Tests OCR capabilities in video content.

PaperLeaderboard

Benchmark Stats

Models6
Papers6
Metrics1

SOTA History

Not enough data to show trend.

Total Accuracy

Overall accuracy across all video OCR tasks

Higher is better

RankModelSourceScoreYearPaper
1gemini-25-pro

1,464 videos, 2,000 QA pairs, 25 tasks

Editorial73.72025Source
2qwen25-vl-72bEditorial692025Source
3internvl3-78bEditorial67.22025Source
4gpt-4oEditorial66.42025Source
5gemini-15-proEditorial64.92025Source
6qwen25-vl-32bEditorial612025Source

Submit a Result

Back to General OCR Capabilities