Codesota · Models · EasyOCRJaidedAI5 results · 3 benchmarks
Model card

EasyOCR.

JaidedAIopen-sourceDeep Learning OCRApache 2.0

80+ languages supported

§ 01 · Benchmarks

Every benchmark EasyOCR has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01videodb's-ocr-benchmark-public-collectionComputer Vision · Optical Character Recognitionwer0.8%#1/52025-02-10source ↗
02videodb's-ocr-benchmark-public-collectionComputer Vision · Optical Character Recognitioncer0.5%#2/52025-02-10source ↗
03sutComputer Vision · Optical Character Recognitioncer0.1%#2/22023-11-27source ↗
04videodb's-ocr-benchmark-public-collectionComputer Vision · Optical Character Recognitionaccuracy49.3%#5/52025-02-10source ↗
05KITAB-BenchComputer Vision · Optical Character Recognitioncer0.6%#7/14source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where EasyOCR actually performs.

Computer Vision
3
benchmarks
avg rank #3.4
§ 03 · Papers

2 papers with results for EasyOCR.

  1. 2025-02-10· Computer Vision· 3 results

    Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments

  2. 2023-11-27· Computer Vision· 1 result

    SUT: a new multi-purpose synthetic dataset for Farsi document image analysis

§ 05 · Sources & freshness

Where these numbers come from.

papers-with-code
4
results
alphaxiv-leaderboard
1
result
4 of 5 rows marked verified. · first result 2023-11-27, latest 2025-02-10.