# Image Quality Description on SPAQ

Source: [Image Quality Description on SPAQ](<https://www.sota2.com/research/sota/image-quality-description-on-spaq>)

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

Data updated: 2026-02-26T05:31:41.138Z

Evaluation of image quality description capabilities on the SPAQ dataset, measured using metrics such as Accuracy, Reasonableness, Completeness, and Confidence.

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 | Image Quality Description |
| Dataset (including any stated split) | SPAQ |
| Metric | Accuracy |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-quality-description-on-spaq.md?metric=Accuracy>): Higher is better; unit: SCALAR.

- [Reasonableness](<https://www.sota2.com/research/sota/image-quality-description-on-spaq.md?metric=Reasonableness>): Higher is better; unit: SCALAR.

- [Completeness](<https://www.sota2.com/research/sota/image-quality-description-on-spaq.md?metric=Completeness>): Higher is better; unit: SCALAR.

- [Confidence](<https://www.sota2.com/research/sota/image-quality-description-on-spaq.md?metric=Confidence>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Zoom-IQA | 8.63 | Not recorded | 695de86853fdd5c361743a7d |
| VisualQuality-R1 | 8.32 | Not recorded | 695de86853fdd5c361743a7d |
| Q-Insight | 7.84 | Not recorded | 695de86853fdd5c361743a7d |
| Zoom-IQA | 6.97 | Not recorded | 695de86853fdd5c361743a7d |
| VisualQuality-R1 | 6.61 | Not recorded | 695de86853fdd5c361743a7d |
| Q-Insight | 6.22 | Not recorded | 695de86853fdd5c361743a7d |
| DepictQA | 6.04 | Not recorded | 695de86853fdd5c361743a7d |
| DepictQA | 4.8 | Not recorded | 695de86853fdd5c361743a7d |

### Zoom-IQA

Accuracy: 8.63. Result ID: 6997e2cc5698665ec43bb93c.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

Recorded evaluation configuration: {"VLM Evaluator":"Gemini-2.5-flash"}. This record does not assert independent reproduction.

### VisualQuality-R1

Accuracy: 8.32. Result ID: 6997e2cc5698665ec43bb938.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c651e209131cea8dd54.md>)

Recorded evaluation configuration: {"VLM Evaluator":"Gemini-2.5-flash"}. This record does not assert independent reproduction.

### Q-Insight

Accuracy: 7.84. Result ID: 6997e2cc5698665ec43bb93a.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b51e209131cea79e58.md>)

Recorded evaluation configuration: {"VLM Evaluator":"Gemini-2.5-flash"}. This record does not assert independent reproduction.

### Zoom-IQA

Accuracy: 6.97. Result ID: 6997e2cc5698665ec43bb93d.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

Recorded evaluation configuration: {"VLM Evaluator":"GPT-5-mini"}. This record does not assert independent reproduction.

### VisualQuality-R1

Accuracy: 6.61. Result ID: 6997e2cc5698665ec43bb939.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c651e209131cea8dd54.md>)

Recorded evaluation configuration: {"VLM Evaluator":"GPT-5-mini"}. This record does not assert independent reproduction.

### Q-Insight

Accuracy: 6.22. Result ID: 6997e2cc5698665ec43bb93b.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b51e209131cea79e58.md>)

Recorded evaluation configuration: {"VLM Evaluator":"GPT-5-mini"}. This record does not assert independent reproduction.

### DepictQA

Accuracy: 6.04. Result ID: 6997e2cc5698665ec43bb936.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74211e209131cea5fd4f.md>)

Recorded evaluation configuration: {"VLM Evaluator":"Gemini-2.5-flash"}. This record does not assert independent reproduction.

### DepictQA

Accuracy: 4.8. Result ID: 6997e2cc5698665ec43bb937.

[Reporting paper](<https://www.sota2.com/research/paper/695de86853fdd5c361743a7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74211e209131cea5fd4f.md>)

Recorded evaluation configuration: {"VLM Evaluator":"GPT-5-mini"}. This record does not assert independent reproduction.

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