# Scene Text Recognition on ArT + COCO-Text + Uber-Text aggregate 36-char (test)

Source: [Scene Text Recognition on ArT + COCO-Text + Uber-Text aggregate 36-char (test)](<https://www.sota2.com/research/sota/scene-text-recognition-on-art-plus-coco-text-plus-uber-text-aggregate-36-char-test>)

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

Data updated: 2026-02-26T06:08:59.560Z

Evaluation of Scene Text Recognition performance on the combined test set aggregating data from ArT, COCO-Text, and Uber-Text, specifically focusing on 36-character sequences, 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 + COCO-Text + Uber-Text aggregate 36-char (test) |
| Metric | Word Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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-plus-coco-text-plus-uber-text-aggregate-36-char-test.md?metric=Word%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Word Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PARSeqA | 84.1 | Not recorded | 68fa6d031e209131cea37551 |
| PARSeqN | 82.1 | Not recorded | 68fa6d031e209131cea37551 |
| TRBA | 81.3 | Not recorded | 68fa6d031e209131cea37551 |
| ViTSTR-S | 78.7 | Not recorded | 68fa6d031e209131cea37551 |
| ABINet | 74.6 | Not recorded | 68fa6d031e209131cea37551 |
| CRNN | 56.3 | Not recorded | 68fa6d031e209131cea37551 |
| PARSeqA | 51.8 | Not recorded | 68fa6d031e209131cea37551 |
| PARSeqN | 49.7 | Not recorded | 68fa6d031e209131cea37551 |
| TRBA | 48.3 | Not recorded | 68fa6d031e209131cea37551 |
| ViTSTR-S | 47 | Not recorded | 68fa6d031e209131cea37551 |
| ABINet | 45.2 | Not recorded | 68fa6d031e209131cea37551 |
| CRNN | 41.1 | Not recorded | 68fa6d031e209131cea37551 |

### PARSeqA

Word Accuracy: 84.1. Result ID: 698f78b03a6c314849f8dda2.

[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: {"Train data":"R"}. This record does not assert independent reproduction.

### PARSeqN

Word Accuracy: 82.1. Result ID: 698f78b03a6c314849f8dda1.

[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: {"Train data":"R"}. This record does not assert independent reproduction.

### TRBA

Word Accuracy: 81.3. Result ID: 698f78b03a6c314849f8dd9f.

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

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

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

### ViTSTR-S

Word Accuracy: 78.7. Result ID: 698f78b03a6c314849f8dd9e.

[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: {"Train data":"R"}. This record does not assert independent reproduction.

### ABINet

Word Accuracy: 74.6. Result ID: 698f78b03a6c314849f8dda0.

[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: {"Train data":"R"}. This record does not assert independent reproduction.

### CRNN

Word Accuracy: 56.3. Result ID: 698f78b03a6c314849f8dd9d.

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

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

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

### PARSeqA

Word Accuracy: 51.8. Result ID: 698f78b03a6c314849f8dd9c.

[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: {"Train data":"S"}. This record does not assert independent reproduction.

### PARSeqN

Word Accuracy: 49.7. Result ID: 698f78b03a6c314849f8dd9b.

[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: {"Train data":"S"}. This record does not assert independent reproduction.

### TRBA

Word Accuracy: 48.3. Result ID: 698f78b03a6c314849f8dd99.

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

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

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

### ViTSTR-S

Word Accuracy: 47. Result ID: 698f78b03a6c314849f8dd98.

[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: {"Train data":"S"}. This record does not assert independent reproduction.

### ABINet

Word Accuracy: 45.2. Result ID: 698f78b03a6c314849f8dd9a.

[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: {"Train data":"S"}. This record does not assert independent reproduction.

### CRNN

Word Accuracy: 41.1. Result ID: 698f78b03a6c314849f8dd97.

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

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

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

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