# Scene Text Recognition on ArT (test)

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

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

Data updated: 2026-02-26T06:09:00.042Z

Evaluation of Scene Text Recognition performance on the test split of the ArT 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) | ArT (test) |
| Metric | Word Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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-art-test.md?metric=Word%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Word Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP4STR-L | 86.4 | Not recorded | 68fa765f1e209131cea6cb50 |
| CLIP4STR-H | 86.4 | Not recorded | 68fa765f1e209131cea6cb50 |
| CLIP4STR-L | 85.9 | Not recorded | 68fa765f1e209131cea6cb50 |
| CLIP4STR-B | 85.8 | Not recorded | 68fa765f1e209131cea6cb50 |
| CLIP4STR-B | 85.8 | Not recorded | 68fa765f1e209131cea6cb50 |
| PARSeq | 84.5 | Not recorded | 68fa765f1e209131cea6cb50 |
| MPSTR | 84.4 | Not recorded | 68fa765f1e209131cea6cb50 |
| ViTSTR-S | 82.5 | Not recorded | 68fa765f1e209131cea6cb50 |
| TRBA | 82.5 | Not recorded | 68fa765f1e209131cea6cb50 |
| ABINet | 81.2 | Not recorded | 68fa765f1e209131cea6cb50 |
| DiG-ViT-B | 81 | Not recorded | 68fa765f1e209131cea6cb50 |
| CLIP4STR-L | 73.7 | Not recorded | 68fa765f1e209131cea6cb50 |
| CLIP4STR-B | 72.8 | Not recorded | 68fa765f1e209131cea6cb50 |
| PARSeq | 70.7 | Not recorded | 68fa765f1e209131cea6cb50 |
| CLIP-OCR | 70.5 | Not recorded | 68fa765f1e209131cea6cb50 |
| MPSTR | 69.9 | Not recorded | 68fa765f1e209131cea6cb50 |
| TRBA | 68.2 | Not recorded | 68fa765f1e209131cea6cb50 |
| ViTSTR-S | 66.1 | Not recorded | 68fa765f1e209131cea6cb50 |
| ABINet | 65.4 | Not recorded | 68fa765f1e209131cea6cb50 |

### CLIP4STR-L

Word Accuracy: 86.4. Result ID: 69941c703a6c3148491b21fe.

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

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

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

Recorded evaluation configuration: {"Train data":"RBU(6.5M)"}. This record does not assert independent reproduction.

### CLIP4STR-H

Word Accuracy: 86.4. Result ID: 69941c703a6c3148491b21ff.

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

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

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

Recorded evaluation configuration: {"Train data":"RBU(6.5M)"}. This record does not assert independent reproduction.

### CLIP4STR-L

Word Accuracy: 85.9. Result ID: 69941c703a6c3148491b21fc.

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

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

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

Recorded evaluation configuration: {"Train data":"Real(3.3M)"}. This record does not assert independent reproduction.

### CLIP4STR-B

Word Accuracy: 85.8. Result ID: 69941c703a6c3148491b21fb.

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

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

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

Recorded evaluation configuration: {"Train data":"Real(3.3M)"}. This record does not assert independent reproduction.

### CLIP4STR-B

Word Accuracy: 85.8. Result ID: 69941c703a6c3148491b21fd.

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

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

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

Recorded evaluation configuration: {"Train data":"RBU(6.5M)"}. This record does not assert independent reproduction.

### PARSeq

Word Accuracy: 84.5. Result ID: 69941c703a6c3148491b21f9.

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

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

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

Recorded evaluation configuration: {"Train data":"Real(3.3M)"}. This record does not assert independent reproduction.

### MPSTR

Word Accuracy: 84.4. Result ID: 69941c703a6c3148491b21fa.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b61e209131cea74eba.md>)

Recorded evaluation configuration: {"Train data":"Real(3.3M)"}. This record does not assert independent reproduction.

### ViTSTR-S

Word Accuracy: 82.5. Result ID: 69941c703a6c3148491b21f6.

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

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

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

Recorded evaluation configuration: {"Train data":"Real(3.3M)"}. This record does not assert independent reproduction.

### TRBA

Word Accuracy: 82.5. Result ID: 69941c703a6c3148491b21f7.

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

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

Recorded evaluation configuration: {"Train data":"Real(3.3M)"}. This record does not assert independent reproduction.

### ABINet

Word Accuracy: 81.2. Result ID: 69941c703a6c3148491b21f8.

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

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

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

Recorded evaluation configuration: {"Train data":"Real(3.3M)"}. This record does not assert independent reproduction.

### DiG-ViT-B

Word Accuracy: 81. Result ID: 69941c703a6c3148491b21f5.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ea91e209131cea412e9.md>)

Recorded evaluation configuration: {"Train data":"Real(2.8M)"}. This record does not assert independent reproduction.

### CLIP4STR-L

Word Accuracy: 73.7. Result ID: 69941c703a6c3148491b21f4.

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

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

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

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

### CLIP4STR-B

Word Accuracy: 72.8. Result ID: 69941c703a6c3148491b21f3.

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

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

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

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

### PARSeq

Word Accuracy: 70.7. Result ID: 69941c703a6c3148491b21f0.

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

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

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

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

### CLIP-OCR

Word Accuracy: 70.5. Result ID: 69941c703a6c3148491b21f2.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cd1e209131cea4d3ec.md>)

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

### MPSTR

Word Accuracy: 69.9. Result ID: 69941c703a6c3148491b21f1.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b61e209131cea74eba.md>)

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

### TRBA

Word Accuracy: 68.2. Result ID: 69941c703a6c3148491b21ee.

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

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

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

### ViTSTR-S

Word Accuracy: 66.1. Result ID: 69941c703a6c3148491b21ed.

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

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

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

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

### ABINet

Word Accuracy: 65.4. Result ID: 69941c703a6c3148491b21ef.

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

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

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

Recorded evaluation configuration: {"Train data":"MJ+ST"}. This record does not assert independent reproduction.

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