Codesota · Benchmark · MME-VideoOCRHome/Leaderboards/MME-VideoOCR
NTU

MME-VideoOCR.

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

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 ↗

Total Accuracy

Total Accuracy is the reported evaluation metric for MME-VideoOCR. 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 Total Accuracyverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01gemini-25-pro
Non-API entry from src
unverified73.72026N/ALooks wrong?
02qwen25-vl-72b
Non-API entry from src
unverified692026N/ALooks wrong?
03internvl3-78b
Non-API entry from src
unverified67.22026N/ALooks wrong?
04gpt-4o
Non-API entry from src
unverified66.42026N/ALooks wrong?
05gemini-15-pro
Non-API entry from src
unverified64.92026N/ALooks wrong?
06qwen25-vl-32b
Non-API entry from src
unverified612026N/ALooks wrong?
§ 04 · Submit a result

Add to the leaderboard.

Submit a Result

Sign in to submit benchmark results for MME-VideoOCR.

Sign in
← Back to Leaderboards