# No-Reference Image Quality Assessment on KonIQ-10K 1.0 (test)

Source: [No-Reference Image Quality Assessment on KonIQ-10K 1.0 (test)](<https://www.sota2.com/research/sota/no-reference-image-quality-assessment-on-koniq-10k-1-0-test>)

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

Data updated: 2026-03-25T13:06:22.821Z

Evaluation of No-Reference Image Quality Assessment performance on the test split of the KonIQ-10K version 1.0 dataset, reporting correlation metrics PLCC and SRCC.

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 | No-Reference Image Quality Assessment |
| Dataset (including any stated split) | KonIQ-10K 1.0 (test) |
| Metric | PLCC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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/no-reference-image-quality-assessment-on-koniq-10k-1-0-test.md?metric=PLCC>): Higher is better; unit: SCALAR.

- [SRCC](<https://www.sota2.com/research/sota/no-reference-image-quality-assessment-on-koniq-10k-1-0-test.md?metric=SRCC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PLCC | Result date | Report paper |
| --- | --- | --- | --- |
| DeQA-Score | 0.953 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| Q-Align | 0.941 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| Q-Insight† | 0.933 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| Q-Tacit† | 0.925 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| MUSIQ | 0.924 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| VisualQuality-R1 | 0.924 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| Compare2Score | 0.923 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| Q-Tacit | 0.923 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| Q-Insight | 0.918 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| CLIP-IQA+ | 0.909 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| NIMA | 0.896 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| Qwen-2.5-VL-7B | 0.889 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| ManIQA | 0.849 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| NIQE | 0.533 | Not recorded | 69c36bfd0636e5bf4afc6436 |
| BRISQUE | 0.225 | Not recorded | 69c36bfd0636e5bf4afc6436 |

### DeQA-Score

PLCC: 0.953. Result ID: 69c3dccc47f34ce924ad3876.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77991e209131cea74442.md>)

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### Q-Align

PLCC: 0.941. Result ID: 69c3dccc47f34ce924ad3875.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a31e209131cea523a2.md>)

[Implementation](<https://github.com/Q-Future/Q-Align>)

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### Q-Insight†

PLCC: 0.933. Result ID: 69c3dccc47f34ce924ad3879.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

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

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Multi-task training set in \[25\] for GRPO calibration"}. This record does not assert independent reproduction.

### Q-Tacit†

PLCC: 0.925. Result ID: 69c3dccc47f34ce924ad387b.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Multi-task training set in \[25\] for GRPO calibration"}. This record does not assert independent reproduction.

### MUSIQ

PLCC: 0.924. Result ID: 69c3dccc47f34ce924ad3870.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a921e209131cea28fa7.md>)

[Implementation](<https://github.com/google-research/google-research/tree/master/musiq>)

Recorded evaluation configuration: {"Method Category":"Non-VLM Deep-learning","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### VisualQuality-R1

PLCC: 0.924. Result ID: 69c3dccc47f34ce924ad3877.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

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

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### Compare2Score

PLCC: 0.923. Result ID: 69c3dccc47f34ce924ad3873.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736b1e209131cea5c604.md>)

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### Q-Tacit

PLCC: 0.923. Result ID: 69c3dccc47f34ce924ad387a.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### Q-Insight

PLCC: 0.918. Result ID: 69c3dccc47f34ce924ad3878.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

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

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### CLIP-IQA+

PLCC: 0.909. Result ID: 69c3dccc47f34ce924ad3871.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfd1e209131cea3d39b.md>)

[Implementation](<https://github.com/IceClear/CLIP-IQA>)

Recorded evaluation configuration: {"Method Category":"Non-VLM Deep-learning","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### NIMA

PLCC: 0.896. Result ID: 69c3dccc47f34ce924ad386f.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64891e209131cea05499.md>)

Recorded evaluation configuration: {"Method Category":"Non-VLM Deep-learning","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### Qwen-2.5-VL-7B

PLCC: 0.889. Result ID: 69c3dccc47f34ce924ad3874.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Method Category":"VLM-based","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### ManIQA

PLCC: 0.849. Result ID: 69c3dccc47f34ce924ad3872.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c551e209131cea3356a.md>)

[Implementation](<https://github.com/IIGROUP/MANIQA>)

Recorded evaluation configuration: {"Method Category":"Non-VLM Deep-learning","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### NIQE

PLCC: 0.533. Result ID: 69c3dccc47f34ce924ad386d.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

Recorded evaluation configuration: {"Method Category":"Handcrafted","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

### BRISQUE

PLCC: 0.225. Result ID: 69c3dccc47f34ce924ad386e.

[Reporting paper](<https://www.sota2.com/research/paper/69c36bfd0636e5bf4afc6436.md>)

Recorded evaluation configuration: {"Method Category":"Handcrafted","Training Protocol":"Trained on KonIQ-10K"}. This record does not assert independent reproduction.

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