Codesota · Benchmark · videodb's-ocr-benchmark-public-collectionHome/Leaderboards/Vision & Documents/Document OCR/videodb's-ocr-benchmark-public-collection
Unknown

videodb's-ocr-benchmark-public-collection.

videodb's-ocr-benchmark-public-collection is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for videodb's-ocr-benchmark-public-collection.

Paper ↗Leaderboard ↓
§ 01 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Accuracy

Accuracy is the reported evaluation metric for videodb's-ocr-benchmark-public-collection. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Accuracyverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01GPT-4o
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified76.222025Paper ↗Code ↗Looks wrong?
02Gemini 1.5 Pro
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified76.132025Paper ↗Code ↗Looks wrong?
03Claude-3 Sonnet
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified67.712025Paper ↗Code ↗Looks wrong?
04RapidOCR
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified56.982025Paper ↗Code ↗Looks wrong?
05EasyOCR
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified49.32025Paper ↗Code ↗Looks wrong?

Wer

Wer is the reported evaluation metric for videodb's-ocr-benchmark-public-collection. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Lower is better

Trust tiers for Werverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01Gemini 1.5 Pro
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.242025Paper ↗Code ↗Looks wrong?
02RapidOCR
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.432025Paper ↗Code ↗Looks wrong?
03Claude-3 Sonnet
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.472025Paper ↗Code ↗Looks wrong?
04GPT-4o
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.512025Paper ↗Code ↗Looks wrong?
05EasyOCR
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.832025Paper ↗Code ↗Looks wrong?

Cer

Cer is the reported evaluation metric for videodb's-ocr-benchmark-public-collection. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Lower is better

Trust tiers for Cerverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01GPT-4o
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.242025Paper ↗Code ↗Looks wrong?
02Gemini 1.5 Pro
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.242025Paper ↗Code ↗Looks wrong?
03Claude-3 Sonnet
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.322025Paper ↗Code ↗Looks wrong?
04EasyOCR
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.512025Paper ↗Code ↗Looks wrong?
05RapidOCR
From paper: Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
verified0.762025Paper ↗Code ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Document OCR