§ 01 · Benchmarks
Every benchmark EasyOCR has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | videodb's-ocr-benchmark-public-collection | Computer Vision · Optical Character Recognition | wer | 0.8% | #1 | 2025-02-10 | source ↗ |
| 02 | videodb's-ocr-benchmark-public-collection | Computer Vision · Optical Character Recognition | cer | 0.5% | #2 | 2025-02-10 | source ↗ |
| 03 | sut | Computer Vision · Optical Character Recognition | cer | 0.1% | #2 | 2023-11-27 | source ↗ |
| 04 | videodb's-ocr-benchmark-public-collection | Computer Vision · Optical Character Recognition | accuracy | 49.3% | #5 | 2025-02-10 | source ↗ |
| 05 | KITAB-Bench | Computer Vision · Optical Character Recognition | cer | 0.6% | #7 | — | source ↗ |
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.
§ 03 · Papers
2 papers with results for EasyOCR.
- 2025-02-10· Computer Vision· 3 results
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
- 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.