# Scene Text Recognition on Six benchmark datasets rotated versions (test)

Source: [Scene Text Recognition on Six benchmark datasets rotated versions (test)](<https://www.sota2.com/research/sota/scene-text-recognition-on-six-benchmark-datasets-rotated-versions-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:08:59.287Z

Evaluation of Scene Text Recognition performance across six different benchmark datasets, specifically testing accuracy under various text rotations (0°, 90°, 180°, 270°).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Scene Text Recognition |
| Dataset (including any stated split) | Six benchmark datasets rotated versions (test) |
| Metric | Word Acc (0°) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Word Acc (0°)](<https://www.sota2.com/research/sota/scene-text-recognition-on-six-benchmark-datasets-rotated-versions-test.md?metric=Word%20Acc%20(0%C2%B0)>): Higher is better; unit: PERCENT.

- [Word Acc (90°)](<https://www.sota2.com/research/sota/scene-text-recognition-on-six-benchmark-datasets-rotated-versions-test.md?metric=Word%20Acc%20(90%C2%B0)>): Higher is better; unit: PERCENT.

- [Word Acc (180°)](<https://www.sota2.com/research/sota/scene-text-recognition-on-six-benchmark-datasets-rotated-versions-test.md?metric=Word%20Acc%20(180%C2%B0)>): Higher is better; unit: PERCENT.

- [Word Acc (270°)](<https://www.sota2.com/research/sota/scene-text-recognition-on-six-benchmark-datasets-rotated-versions-test.md?metric=Word%20Acc%20(270%C2%B0)>): Higher is better; unit: PERCENT.

- [Mean Word Acc](<https://www.sota2.com/research/sota/scene-text-recognition-on-six-benchmark-datasets-rotated-versions-test.md?metric=Mean%20Word%20Acc>): Higher is better; unit: PERCENT.

- [% Decrease](<https://www.sota2.com/research/sota/scene-text-recognition-on-six-benchmark-datasets-rotated-versions-test.md?metric=%25%20Decrease>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Word Acc (0°) | Result date | Report paper |
| --- | --- | --- | --- |
| PARSeq | 93.3 | Not recorded | 68fa6d031e209131cea37551 |
| PARSeq | 92.7 | Not recorded | 68fa6d031e209131cea37551 |
| TRBA | 92.5 | Not recorded | 68fa6d031e209131cea37551 |
| ABINet | 92.4 | Not recorded | 68fa6d031e209131cea37551 |
| ViTSTR-S | 91.8 | Not recorded | 68fa6d031e209131cea37551 |
| CRNN | 85.8 | Not recorded | 68fa6d031e209131cea37551 |

### PARSeq

Word Acc (0°): 93.3. Result ID: 698f78b03a6c314849f8ddb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Implementation](<https://github.com/baudm/parseq>)

Recorded evaluation configuration: {"variant":"A"}. This record does not assert independent reproduction.

### PARSeq

Word Acc (0°): 92.7. Result ID: 698f78b03a6c314849f8ddb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Implementation](<https://github.com/baudm/parseq>)

Recorded evaluation configuration: {"variant":"N"}. This record does not assert independent reproduction.

### TRBA

Word Acc (0°): 92.5. Result ID: 698f78b03a6c314849f8ddb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa626b1e209131ce9f94bb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ABINet

Word Acc (0°): 92.4. Result ID: 698f78b03a6c314849f8ddb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea227bf.md>)

[Implementation](<https://github.com/FangShancheng/ABINet>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ViTSTR-S

Word Acc (0°): 91.8. Result ID: 698f78b03a6c314849f8ddb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ef1e209131cea250ab.md>)

[Implementation](<https://github.com/roatienza/deep-text-recognition-benchmark>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CRNN

Word Acc (0°): 85.8. Result ID: 698f78b03a6c314849f8ddaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea37551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea26339.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
