# Audio Retrieval on Clotho

Source: [Audio Retrieval on Clotho](<https://www.sota2.com/research/sota/audio-retrieval-on-clotho>)

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

Data updated: 2026-05-19T12:49:44.705Z

Evaluation of Audio Retrieval performance on the Clotho dataset, typically measured using metrics like R@1 and R@10.

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 | Audio Retrieval |
| Dataset (including any stated split) | Clotho |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 33 of 33 |
| 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

- [R@1](<https://www.sota2.com/research/sota/audio-retrieval-on-clotho.md?metric=R%401>): Higher is better; unit: PERCENT.

- [R@10](<https://www.sota2.com/research/sota/audio-retrieval-on-clotho.md?metric=R%4010>): Higher is better; unit: PERCENT.

- [R@5](<https://www.sota2.com/research/sota/audio-retrieval-on-clotho.md?metric=R%405>): Higher is better; unit: PERCENT.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| CLAP | 23.7 | Not recorded | 68fa700d1e209131cea48e29 |
| MAViL | 23.3 | Not recorded | 68fa700d1e209131cea48e29 |
| OmniBind | 23.3 | Not recorded | 6a0bef0bdbc836b87d82c9f0 |
| MAViL | 17.2 | Not recorded | 68fa700d1e209131cea48e29 |
| LanguageBind | 16.7 | Not recorded | 6a0bef0bdbc836b87d82c9f0 |
| ML-ACT | 16.2 | Not recorded | 68fa700d1e209131cea48e29 |
| CLAP | 15.6 | Not recorded | 68fa700d1e209131cea48e29 |
| CyCLAPS | 14.93 | Not recorded | 68fa70e91e209131cea4def1 |
| CyCLAP | 14.74 | Not recorded | 68fa70e91e209131cea4def1 |
| ML-ACT | 14.4 | Not recorded | 68fa700d1e209131cea48e29 |
| CLAP | 13.88 | Not recorded | 68fa70e91e209131cea4def1 |
| FreeBind | 13.7 | Not recorded | 6a0bef0bdbc836b87d82c9f0 |
| CLAPS | 13.49 | Not recorded | 68fa70e91e209131cea4def1 |
| ARNLQ | 12.6 | Not recorded | 68fa6f971e209131cea467c4 |
| LanguageBind | 12.1 | Not recorded | 69ddca687d0172140ec79e7d |
| EmergentBridge | 11.7 | Not recorded | 69ddca687d0172140ec79e7d |
| EmergentBridge | 10 | Not recorded | 69ddca687d0172140ec79e7d |
| CodeBind-VL | 8.5 | Not recorded | 6a0bef0bdbc836b87d82c9f0 |
| AVFIC finetuned | 8.4 | Not recorded | 68fa6f971e209131cea467c4 |
| C-MCR | 8.37 | Not recorded | 69ddca687d0172140ec79e7d |
| ViT-LENS\_L | 8.1 | Not recorded | 68fa72b21e209131cea57f66 |
| MMT | 7 | Not recorded | 68fa700d1e209131cea48e29 |
| CodeBind-IB | 6.9 | Not recorded | 6a0bef0bdbc836b87d82c9f0 |
| ViT-LENS\_L | 6.8 | Not recorded | 68fa72b21e209131cea57f66 |
| MMT | 6.7 | Not recorded | 68fa700d1e209131cea48e29 |
| ImageBind-H | 6 | Not recorded | 68fa72b21e209131cea57f66 |
| IMAGEBIND | 6 | Not recorded | 68fa6f971e209131cea467c4 |
| ImageBind | 6 | Not recorded | 69ddca687d0172140ec79e7d |
| AudioCLIP | 3.2 | Not recorded | 69ddca687d0172140ec79e7d |
| AVFIC | 3 | Not recorded | 68fa72b21e209131cea57f66 |
| AVFIC | 3 | Not recorded | 68fa6f971e209131cea467c4 |
| AVFIC | 3 | Not recorded | 69ddca687d0172140ec79e7d |
| WAV2CLIP | 0.78 | Not recorded | 69ddca687d0172140ec79e7d |

### CLAP

R@1: 23.7. Result ID: 699118f63a6c31484905a9bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729e1e209131cea57959.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MAViL

R@1: 23.3. Result ID: 699118f63a6c31484905a9be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Implementation](<https://github.com/facebookresearch/MAViL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OmniBind

R@1: 23.3. Result ID: 6a0c5c57fbc373592c03eeae.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bef0bdbc836b87d82c9f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fce7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MAViL

R@1: 17.2. Result ID: 699118f63a6c31484905a9ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Implementation](<https://github.com/facebookresearch/MAViL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LanguageBind

R@1: 16.7. Result ID: 6a0c5c57fbc373592c03eeaf.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bef0bdbc836b87d82c9f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71f31e209131cea53b97.md>)

[Implementation](<https://github.com/PKU-YuanGroup/LanguageBind>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ML-ACT

R@1: 16.2. Result ID: 699118f63a6c31484905a9bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5e1e209131cea27c62.md>)

Recorded evaluation configuration: {"trained without LAION-630K":true}. This record does not assert independent reproduction.

### CLAP

R@1: 15.6. Result ID: 699118f63a6c31484905a9b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729e1e209131cea57959.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CyCLAPS

R@1: 14.93. Result ID: 69917d843a6c314849087f47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4def1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4def1.md>)

Recorded evaluation configuration: {"sentence embedding training":"unsupervised (Ls)"}. This record does not assert independent reproduction.

### CyCLAP

R@1: 14.74. Result ID: 69917d843a6c314849087f46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4def1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c046.md>)

[Implementation](<https://github.com/goel-shashank/CyCLIP>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ML-ACT

R@1: 14.4. Result ID: 699118f63a6c31484905a9b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5e1e209131cea27c62.md>)

Recorded evaluation configuration: {"trained without LAION-630K":true}. This record does not assert independent reproduction.

### CLAP

R@1: 13.88. Result ID: 69917d843a6c314849087f44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4def1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729e1e209131cea57959.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FreeBind

R@1: 13.7. Result ID: 6a0c5c57fbc373592c03eead.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bef0bdbc836b87d82c9f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73241e209131cea5aa3e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CLAPS

R@1: 13.49. Result ID: 69917d843a6c314849087f45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4def1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4def1.md>)

Recorded evaluation configuration: {"sentence embedding training":"unsupervised (Ls)"}. This record does not assert independent reproduction.

### ARNLQ

R@1: 12.6. Result ID: 69a1537535dfcabb00e648a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a761e209131cea284fa.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/research/audio-retrieval/>)

Recorded evaluation configuration: {"Emergent":"false","Supervision":"Supervised"}. This record does not assert independent reproduction.

### LanguageBind

R@1: 12.1. Result ID: 69de213047f34ce924c684dd.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71f31e209131cea53b97.md>)

[Implementation](<https://github.com/PKU-YuanGroup/LanguageBind>)

Recorded evaluation configuration: {"Anchor Modality":"Text"}. This record does not assert independent reproduction.

### EmergentBridge

R@1: 11.7. Result ID: 69de213047f34ce924c684de.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

Recorded evaluation configuration: {"Anchor Modality":"Text"}. This record does not assert independent reproduction.

### EmergentBridge

R@1: 10. Result ID: 69de213047f34ce924c684e0.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

Recorded evaluation configuration: {"Anchor Modality":"Image","Evaluation Protocol":"emergent zero-shot"}. This record does not assert independent reproduction.

### CodeBind-VL

R@1: 8.5. Result ID: 6a0c5c57fbc373592c03eeb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bef0bdbc836b87d82c9f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bef0bdbc836b87d82c9f0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AVFIC finetuned

R@1: 8.4. Result ID: 69a1537535dfcabb00e648a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32ceb.md>)

Recorded evaluation configuration: {"Emergent":"false","Supervision":"Supervised"}. This record does not assert independent reproduction.

### C-MCR

R@1: 8.37. Result ID: 69de213047f34ce924c684dc.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dd0e.md>)

[Implementation](<https://c-mcr.github.io/C-MCR/>)

Recorded evaluation configuration: {"Anchor Modality":"–"}. This record does not assert independent reproduction.

### ViT-LENS\_L

R@1: 8.1. Result ID: 69926e143a6c3148490ee617.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Implementation](<https://github.com/TencentARC/ViT-Lens>)

Recorded evaluation configuration: {"anchor":"I+T"}. This record does not assert independent reproduction.

### MMT

R@1: 7. Result ID: 699118f63a6c31484905a9bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a761e209131cea284fa.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/research/audio-retrieval/>)

Recorded evaluation configuration: {"trained without LAION-630K":true}. This record does not assert independent reproduction.

### CodeBind-IB

R@1: 6.9. Result ID: 6a0c5c57fbc373592c03eeb0.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bef0bdbc836b87d82c9f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bef0bdbc836b87d82c9f0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ViT-LENS\_L

R@1: 6.8. Result ID: 69926e143a6c3148490ee616.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Implementation](<https://github.com/TencentARC/ViT-Lens>)

Recorded evaluation configuration: {"anchor":"I"}. This record does not assert independent reproduction.

### MMT

R@1: 6.7. Result ID: 699118f63a6c31484905a9b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a761e209131cea284fa.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/research/audio-retrieval/>)

Recorded evaluation configuration: {"trained without LAION-630K":true}. This record does not assert independent reproduction.

### ImageBind-H

R@1: 6. Result ID: 69926e143a6c3148490ee615.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Implementation](<https://facebookresearch.github.io/ImageBind>)

Recorded evaluation configuration: {"anchor":"I"}. This record does not assert independent reproduction.

### IMAGEBIND

R@1: 6. Result ID: 69a1537535dfcabb00e648a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Implementation](<https://facebookresearch.github.io/ImageBind>)

Recorded evaluation configuration: {"Emergent":"true","Supervision":"No audio and text supervision"}. This record does not assert independent reproduction.

### ImageBind

R@1: 6. Result ID: 69de213047f34ce924c684df.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Implementation](<https://facebookresearch.github.io/ImageBind>)

Recorded evaluation configuration: {"Anchor Modality":"Image","Evaluation Protocol":"emergent zero-shot"}. This record does not assert independent reproduction.

### AudioCLIP

R@1: 3.2. Result ID: 69de213047f34ce924c684da.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d6a1e209131cea39b2c.md>)

[Implementation](<https://github.com/AndreyGuzhov/AudioCLIP>)

Recorded evaluation configuration: {"Anchor Modality":"–"}. This record does not assert independent reproduction.

### AVFIC

R@1: 3. Result ID: 69926e143a6c3148490ee614.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32ceb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AVFIC

R@1: 3. Result ID: 69a1537535dfcabb00e648a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32ceb.md>)

Recorded evaluation configuration: {"Emergent":"false","Supervision":"Uses audio and text loss"}. This record does not assert independent reproduction.

### AVFIC

R@1: 3. Result ID: 69de213047f34ce924c684d9.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32ceb.md>)

Recorded evaluation configuration: {"Anchor Modality":"–"}. This record does not assert independent reproduction.

### WAV2CLIP

R@1: 0.78. Result ID: 69de213047f34ce924c684db.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca687d0172140ec79e7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea3085f.md>)

Recorded evaluation configuration: {"Anchor Modality":"–"}. This record does not assert independent reproduction.

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