# Video Quality Comparison on KoNViD-1K

Source: [Video Quality Comparison on KoNViD-1K](<https://www.sota2.com/research/sota/video-quality-comparison-on-konvid-1k>)

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

Data updated: 2026-02-26T05:31:31.521Z

Evaluation of video quality comparison performance using the KoNViD-1K dataset, measured using 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 | Video Quality Comparison |
| Dataset (including any stated split) | KoNViD-1K |
| Metric | Accuracy |
| Unit | PERCENT |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/video-quality-comparison-on-konvid-1k.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| VQAThinker | 87.17 | Not recorded | 697846c7a2b28e761d87c6e3 |
| VQA^2 | 86.5 | Not recorded | 697846c7a2b28e761d87c6e3 |
| Q-Align | 86.17 | Not recorded | 697846c7a2b28e761d87c6e3 |
| DOVER | 85.5 | Not recorded | 697846c7a2b28e761d87c6e3 |
| FAST-VQA | 84.17 | Not recorded | 697846c7a2b28e761d87c6e3 |
| COVER | 84.17 | Not recorded | 697846c7a2b28e761d87c6e3 |
| MinimalisticVQA | 83.33 | Not recorded | 697846c7a2b28e761d87c6e3 |
| QualiRAG | 80.33 | Not recorded | 697846c7a2b28e761d87c6e3 |
| Co-Instruct | 76.5 | Not recorded | 697846c7a2b28e761d87c6e3 |
| LLaVA-OneVision-7B | 75.33 | Not recorded | 697846c7a2b28e761d87c6e3 |
| Qwen3-VL-8B | 75.33 | Not recorded | 697846c7a2b28e761d87c6e3 |
| Qwen2.5-VL-7B | 73.5 | Not recorded | 697846c7a2b28e761d87c6e3 |
| InternVL3.5-8B | 73.33 | Not recorded | 697846c7a2b28e761d87c6e3 |
| InternVL3-9B | 71 | Not recorded | 697846c7a2b28e761d87c6e3 |
| Q-Instruct | 56.5 | Not recorded | 697846c7a2b28e761d87c6e3 |

### VQAThinker

Accuracy: 87.17. Result ID: 69978da55698665ec4e2cceb.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a871e209131cea83b78.md>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Quality scoring-based","Category":"LMM-based VQA Methods"}. This record does not assert independent reproduction.

### VQA^2

Accuracy: 86.5. Result ID: 69978da55698665ec4e2ccea.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae3b.md>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Quality scoring-based","Category":"LMM-based VQA Methods"}. This record does not assert independent reproduction.

### Q-Align

Accuracy: 86.17. Result ID: 69978da55698665ec4e2cce7.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

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

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

Recorded evaluation configuration: {"Labels":true,"Method Type":"Quality scoring-based","Category":"LMM-based VQA Methods"}. This record does not assert independent reproduction.

### DOVER

Accuracy: 85.5. Result ID: 69978da55698665ec4e2cce4.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb71e209131cea41b5c.md>)

[Implementation](<https://github.com/VQAssessment/DOVER>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Quality scoring-based","Category":"DNN-based VQA Methods"}. This record does not assert independent reproduction.

### FAST-VQA

Accuracy: 84.17. Result ID: 69978da55698665ec4e2cce3.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfa1e209131cea370cf.md>)

[Implementation](<https://github.com/timothyhtimothy/FAST-VQA>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Quality scoring-based","Category":"DNN-based VQA Methods"}. This record does not assert independent reproduction.

### COVER

Accuracy: 84.17. Result ID: 69978da55698665ec4e2cce5.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Quality scoring-based","Category":"DNN-based VQA Methods"}. This record does not assert independent reproduction.

### MinimalisticVQA

Accuracy: 83.33. Result ID: 69978da55698665ec4e2cce6.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea582df.md>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Quality scoring-based","Category":"DNN-based VQA Methods"}. This record does not assert independent reproduction.

### QualiRAG

Accuracy: 80.33. Result ID: 69978da55698665ec4e2ccec.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

Recorded evaluation configuration: {"Labels":false,"Method Type":"Question-answering-based","Category":"Ours RAG-based Method"}. This record does not assert independent reproduction.

### Co-Instruct

Accuracy: 76.5. Result ID: 69978da55698665ec4e2cce9.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72651e209131cea56305.md>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Question-answering-based","Category":"LMM-based VQA Methods"}. This record does not assert independent reproduction.

### LLaVA-OneVision-7B

Accuracy: 75.33. Result ID: 69978da55698665ec4e2ccde.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e58.md>)

[Implementation](<https://llava-vl.github.io/blog/llava-onevision>)

Recorded evaluation configuration: {"Labels":false,"Method Type":"Question-answering-based","Category":"Open-sourced General-purpose LMMs"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Accuracy: 75.33. Result ID: 69978da55698665ec4e2cce2.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

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

Recorded evaluation configuration: {"Labels":false,"Method Type":"Question-answering-based","Category":"Open-sourced General-purpose LMMs"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Accuracy: 73.5. Result ID: 69978da55698665ec4e2cce1.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

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

Recorded evaluation configuration: {"Labels":false,"Method Type":"Question-answering-based","Category":"Open-sourced General-purpose LMMs"}. This record does not assert independent reproduction.

### InternVL3.5-8B

Accuracy: 73.33. Result ID: 69978da55698665ec4e2cce0.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85dc9.md>)

Recorded evaluation configuration: {"Labels":false,"Method Type":"Question-answering-based","Category":"Open-sourced General-purpose LMMs"}. This record does not assert independent reproduction.

### InternVL3-9B

Accuracy: 71. Result ID: 69978da55698665ec4e2ccdf.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Labels":false,"Method Type":"Question-answering-based","Category":"Open-sourced General-purpose LMMs"}. This record does not assert independent reproduction.

### Q-Instruct

Accuracy: 56.5. Result ID: 69978da55698665ec4e2cce8.

[Reporting paper](<https://www.sota2.com/research/paper/697846c7a2b28e761d87c6e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa712c1e209131cea4fb99.md>)

Recorded evaluation configuration: {"Labels":true,"Method Type":"Question-answering-based","Category":"LMM-based VQA Methods"}. This record does not assert independent reproduction.

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