# Text Quality Assessment on TIQA-Images

Source: [Text Quality Assessment on TIQA-Images](<https://www.sota2.com/research/sota/text-quality-assessment-on-tiqa-images>)

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

Data updated: 2026-03-10T08:50:08.382Z

Evaluation of Text Quality Assessment performance on the TIQA-Images dataset, typically measured using correlation metrics like PLCC and SROCC, alongside MOS-related scores.

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 | Text Quality Assessment |
| Dataset (including any stated split) | TIQA-Images |
| Metric | PLCC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [PLCC](<https://www.sota2.com/research/sota/text-quality-assessment-on-tiqa-images.md?metric=PLCC>): Higher is better; unit: SCALAR.

- [SROCC](<https://www.sota2.com/research/sota/text-quality-assessment-on-tiqa-images.md?metric=SROCC>): Higher is better; unit: SCALAR.

- [Selected MOS](<https://www.sota2.com/research/sota/text-quality-assessment-on-tiqa-images.md?metric=Selected%20MOS>): Higher is better; unit: SCALAR.

- [ΔMOS vs Random](<https://www.sota2.com/research/sota/text-quality-assessment-on-tiqa-images.md?metric=%CE%94MOS%20vs%20Random>): Higher is better; unit: SCALAR.

- [Gap Closed](<https://www.sota2.com/research/sota/text-quality-assessment-on-tiqa-images.md?metric=Gap%20Closed>): Higher is better; unit: PERCENT.

## Recorded results

| Method | PLCC | Result date | Report paper |
| --- | --- | --- | --- |
| ANTIQA | 0.842 | Not recorded | 69afa56a2d603e6de3e438d3 |
| PaddleOCR | 0.761 | Not recorded | 69afa56a2d603e6de3e438d3 |
| SAR | 0.634 | Not recorded | 69afa56a2d603e6de3e438d3 |
| TOPIQ | 0.493 | Not recorded | 69afa56a2d603e6de3e438d3 |
| Qwen3 | 0.447 | Not recorded | 69afa56a2d603e6de3e438d3 |
| ANTIQA | 0.419 | Not recorded | 69afa56a2d603e6de3e438d3 |
| PaddleOCR | 0.415 | Not recorded | 69afa56a2d603e6de3e438d3 |
| SAR | 0.325 | Not recorded | 69afa56a2d603e6de3e438d3 |
| Qwen3\*\* | 0.265 | Not recorded | 69afa56a2d603e6de3e438d3 |
| GLM 4.6 | 0.193 | Not recorded | 69afa56a2d603e6de3e438d3 |
| GLM 4.6\*\* | 0.185 | Not recorded | 69afa56a2d603e6de3e438d3 |
| Qwen3\* | 0.181 | Not recorded | 69afa56a2d603e6de3e438d3 |
| GLM 4.6\* | 0.148 | Not recorded | 69afa56a2d603e6de3e438d3 |
| TOPIQ | 0.115 | Not recorded | 69afa56a2d603e6de3e438d3 |
| Qwen3 | 0.06 | Not recorded | 69afa56a2d603e6de3e438d3 |
| GLM 4.6 | 0.027 | Not recorded | 69afa56a2d603e6de3e438d3 |

### ANTIQA

PLCC: 0.842. Result ID: 69afdb3b6dbb7075b9584c77.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

Recorded evaluation configuration: {"Type":"TIQA","Speed (FPS)":"119.0"}. This record does not assert independent reproduction.

### PaddleOCR

PLCC: 0.761. Result ID: 69afdb3b6dbb7075b9584c73.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79f11e209131cea802a7.md>)

Recorded evaluation configuration: {"Type":"OCR","Speed (FPS)":"133.3"}. This record does not assert independent reproduction.

### SAR

PLCC: 0.634. Result ID: 69afdb3b6dbb7075b9584c74.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65861e209131cea0ad98.md>)

[Implementation](<https://tinyurl.com/ShowAttendRead>)

Recorded evaluation configuration: {"Type":"OCR","Speed (FPS)":"19.1"}. This record does not assert independent reproduction.

### TOPIQ

PLCC: 0.493. Result ID: 69afdb3b6dbb7075b9584c72.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703a1e209131cea49bdc.md>)

[Implementation](<https://github.com/chaofengc/IQA-PyTorch>)

Recorded evaluation configuration: {"Type":"IQA","Speed (FPS)":"56.8"}. This record does not assert independent reproduction.

### Qwen3

PLCC: 0.447. Result ID: 69afdb3b6dbb7075b9584c75.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Type":"VLM","Speed (FPS)":"0.6"}. This record does not assert independent reproduction.

### ANTIQA

PLCC: 0.419. Result ID: 69afdb3b6dbb7075b9584c59.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

Recorded evaluation configuration: {"Model Type":"TIQA","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### PaddleOCR

PLCC: 0.415. Result ID: 69afdb3b6dbb7075b9584c51.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79f11e209131cea802a7.md>)

Recorded evaluation configuration: {"Model Type":"OCR","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### SAR

PLCC: 0.325. Result ID: 69afdb3b6dbb7075b9584c52.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65861e209131cea0ad98.md>)

[Implementation](<https://tinyurl.com/ShowAttendRead>)

Recorded evaluation configuration: {"Model Type":"OCR","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### Qwen3\*\*

PLCC: 0.265. Result ID: 69afdb3b6dbb7075b9584c55.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Type":"VLM","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### GLM 4.6

PLCC: 0.193. Result ID: 69afdb3b6dbb7075b9584c76.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

Recorded evaluation configuration: {"Type":"VLM","Speed (FPS)":"0.4"}. This record does not assert independent reproduction.

### GLM 4.6\*\*

PLCC: 0.185. Result ID: 69afdb3b6dbb7075b9584c58.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

Recorded evaluation configuration: {"Model Type":"VLM","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### Qwen3\*

PLCC: 0.181. Result ID: 69afdb3b6dbb7075b9584c54.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Type":"VLM","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### GLM 4.6\*

PLCC: 0.148. Result ID: 69afdb3b6dbb7075b9584c57.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

Recorded evaluation configuration: {"Model Type":"VLM","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### TOPIQ

PLCC: 0.115. Result ID: 69afdb3b6dbb7075b9584c50.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703a1e209131cea49bdc.md>)

[Implementation](<https://github.com/chaofengc/IQA-PyTorch>)

Recorded evaluation configuration: {"Model Type":"IQA","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### Qwen3

PLCC: 0.06. Result ID: 69afdb3b6dbb7075b9584c53.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Type":"VLM","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

### GLM 4.6

PLCC: 0.027. Result ID: 69afdb3b6dbb7075b9584c56.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56a2d603e6de3e438d3.md>)

Recorded evaluation configuration: {"Model Type":"VLM","Selection Strategy":"Best-of-5"}. This record does not assert independent reproduction.

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