# Scene Text Recognition on WOST

Source: [Scene Text Recognition on WOST](<https://www.sota2.com/research/sota/scene-text-recognition-on-wost>)

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

Data updated: 2026-02-26T06:09:00.310Z

Evaluation of Scene Text Recognition performance on the WOST dataset, measured by Word Accuracy.

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) | WOST |
| Metric | Word Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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 Accuracy](<https://www.sota2.com/research/sota/scene-text-recognition-on-wost.md?metric=Word%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Word Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CSD-B | 91.2 | Not recorded | 68fa77801e209131cea73a1b |
| CSD-S | 90.9 | Not recorded | 68fa77801e209131cea73a1b |
| CLIP4STR-H | 90.9 | Not recorded | 68fa77801e209131cea73a1b |
| CSD-D | 90.8 | Not recorded | 68fa77801e209131cea73a1b |
| CLIP4STR-L | 90.6 | Not recorded | 68fa77801e209131cea73a1b |
| CSD-D | 90.6 | Not recorded | 68fa77801e209131cea73a1b |
| CSD-B | 90 | Not recorded | 68fa77801e209131cea73a1b |
| CSD-S | 89.5 | Not recorded | 68fa77801e209131cea73a1b |
| CLIP4STR-L | 89.2 | Not recorded | 68fa77801e209131cea73a1b |
| CLIP4STR-B | 88.8 | Not recorded | 68fa77801e209131cea73a1b |
| CLIP4STR-B | 87.5 | Not recorded | 68fa77801e209131cea73a1b |
| PARSeq | 85.4 | Not recorded | 68fa77801e209131cea73a1b |
| ABINET | 85 | Not recorded | 68fa77801e209131cea73a1b |
| VITSTR-S | 77.9 | Not recorded | 68fa77801e209131cea73a1b |

### CSD-B

Word Accuracy: 91.2. Result ID: 699498703a6c3148491e4456.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

Recorded evaluation configuration: {"Data":"RBU","Params":"104.9 M"}. This record does not assert independent reproduction.

### CSD-S

Word Accuracy: 90.9. Result ID: 699498703a6c3148491e444f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

Recorded evaluation configuration: {"Data":"Real","Params":"40.8 M"}. This record does not assert independent reproduction.

### CLIP4STR-H

Word Accuracy: 90.9. Result ID: 699498703a6c3148491e4454.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765f1e209131cea6cb50.md>)

[Implementation](<https://github.com/VamosC/CLIP4STR>)

Recorded evaluation configuration: {"Data":"RBU","Params":"1 B"}. This record does not assert independent reproduction.

### CSD-D

Word Accuracy: 90.8. Result ID: 699498703a6c3148491e4451.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

Recorded evaluation configuration: {"Data":"Real","Params":"110.2 M"}. This record does not assert independent reproduction.

### CLIP4STR-L

Word Accuracy: 90.6. Result ID: 699498703a6c3148491e4453.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765f1e209131cea6cb50.md>)

[Implementation](<https://github.com/VamosC/CLIP4STR>)

Recorded evaluation configuration: {"Data":"RBU","Params":"446 M"}. This record does not assert independent reproduction.

### CSD-D

Word Accuracy: 90.6. Result ID: 699498703a6c3148491e4457.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

Recorded evaluation configuration: {"Data":"RBU","Params":"110.2 M"}. This record does not assert independent reproduction.

### CSD-B

Word Accuracy: 90. Result ID: 699498703a6c3148491e4450.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

Recorded evaluation configuration: {"Data":"Real","Params":"104.9 M"}. This record does not assert independent reproduction.

### CSD-S

Word Accuracy: 89.5. Result ID: 699498703a6c3148491e4455.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

Recorded evaluation configuration: {"Data":"RBU","Params":"40.8 M"}. This record does not assert independent reproduction.

### CLIP4STR-L

Word Accuracy: 89.2. Result ID: 699498703a6c3148491e444e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765f1e209131cea6cb50.md>)

[Implementation](<https://github.com/VamosC/CLIP4STR>)

Recorded evaluation configuration: {"Data":"Real","Params":"446 M"}. This record does not assert independent reproduction.

### CLIP4STR-B

Word Accuracy: 88.8. Result ID: 699498703a6c3148491e4452.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765f1e209131cea6cb50.md>)

[Implementation](<https://github.com/VamosC/CLIP4STR>)

Recorded evaluation configuration: {"Data":"RBU","Params":"158 M"}. This record does not assert independent reproduction.

### CLIP4STR-B

Word Accuracy: 87.5. Result ID: 699498703a6c3148491e444d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765f1e209131cea6cb50.md>)

[Implementation](<https://github.com/VamosC/CLIP4STR>)

Recorded evaluation configuration: {"Data":"Real","Params":"158 M"}. This record does not assert independent reproduction.

### PARSeq

Word Accuracy: 85.4. Result ID: 699498703a6c3148491e444c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

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

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

Recorded evaluation configuration: {"Data":"Real","Params":"22.5 M"}. This record does not assert independent reproduction.

### ABINET

Word Accuracy: 85. Result ID: 699498703a6c3148491e444b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

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

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

Recorded evaluation configuration: {"Data":"Real","Params":"23.5 M"}. This record does not assert independent reproduction.

### VITSTR-S

Word Accuracy: 77.9. Result ID: 699498703a6c3148491e444a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77801e209131cea73a1b.md>)

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

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

Recorded evaluation configuration: {"Data":"Real","Params":"21.7 M"}. This record does not assert independent reproduction.

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