# Text-to-Image Retrieval on SARVLM-1M (test)

Source: [Text-to-Image Retrieval on SARVLM-1M (test)](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-sarvlm-1m-test>)

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

Data updated: 2026-05-18T06:57:40.802Z

Evaluation of Text-to-Image Retrieval performance on the test split of the SARVLM-1M dataset, measured using R@1, R@5, 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 | Text-to-Image Retrieval |
| Dataset (including any stated split) | SARVLM-1M (test) |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 25 of 25 |
| 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/text-to-image-retrieval-on-sarvlm-1m-test.md?metric=R%401>): Higher is better; unit: PERCENT.

- [R@5](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-sarvlm-1m-test.md?metric=R%405>): Higher is better; unit: PERCENT.

- [R@10](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-sarvlm-1m-test.md?metric=R%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| SARCLIP † | 13.58 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP | 12.88 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP ‡ | 12.88 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP § | 12.86 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP † | 11.3 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP | 10.84 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP § | 10.56 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP ‡ | 10.16 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP | 9.38 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP ‡ | 9.22 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP-ISPRS | 0.46 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SAR-TEXT | 0.42 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP-ISPRS | 0.26 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| RemoteCLIP | 0.24 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SARCLIP-ISPRS | 0.24 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| GeoRSCLIP | 0.2 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| GeoRSCLIP | 0.2 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SkyCLIP | 0.2 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| SkyCLIP | 0.18 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| GeoRSCLIP | 0.12 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| OpenCLIP | 0.1 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| RemoteCLIP | 0.1 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| RemoteCLIP | 0.1 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| OpenCLIP | 0.08 | Not recorded | 69004ded3ef7ccd74e5e29e3 |
| OpenCLIP | 0.06 | Not recorded | 69004ded3ef7ccd74e5e29e3 |

### SARCLIP †

R@1: 13.58. Result ID: 6a0ab79b47f34ce924f04791.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"RS5M","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP

R@1: 12.88. Result ID: 6a0ab79b47f34ce924f04790.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"LAION","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP ‡

R@1: 12.88. Result ID: 6a0ab79b47f34ce924f04793.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"R3+D10+S4","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP §

R@1: 12.86. Result ID: 6a0ab79b47f34ce924f04792.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"SkyScript","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP †

R@1: 11.3. Result ID: 6a0ab79b47f34ce924f0478b.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"RS5M","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP

R@1: 10.84. Result ID: 6a0ab79b47f34ce924f0478a.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"LAION","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP §

R@1: 10.56. Result ID: 6a0ab79b47f34ce924f0478c.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"SkyScript","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP ‡

R@1: 10.16. Result ID: 6a0ab79b47f34ce924f0478d.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"R3+D10+S4","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP

R@1: 9.38. Result ID: 6a0ab79b47f34ce924f04787.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ResNet-50","Pretrain Data":"LAION","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP ‡

R@1: 9.22. Result ID: 6a0ab79b47f34ce924f04788.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ResNet-50","Pretrain Data":"R3+D10+S4","Tune On":"SARVLM-1M"}. This record does not assert independent reproduction.

### SARCLIP-ISPRS

R@1: 0.46. Result ID: 6a0ab79b47f34ce924f0478f.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"LAION","Tune On":"SARCAP"}. This record does not assert independent reproduction.

### SAR-TEXT

R@1: 0.42. Result ID: 6a0ab79b47f34ce924f0478e.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be61e209131cea8b2de.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"LAION","Tune On":"SARTEXT"}. This record does not assert independent reproduction.

### SARCLIP-ISPRS

R@1: 0.26. Result ID: 6a0ab79b47f34ce924f04789.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"–","Tune On":"–"}. This record does not assert independent reproduction.

### RemoteCLIP

R@1: 0.24. Result ID: 6a0ab79b47f34ce924f04783.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea596e5.md>)

[Implementation](<https://github.com/ChenDelong1999/RemoteCLIP>)

Recorded evaluation configuration: {"Image Backbone":"ResNet-50","Pretrain Data":"LAION","Tune On":"R3+D10+S4"}. This record does not assert independent reproduction.

### SARCLIP-ISPRS

R@1: 0.24. Result ID: 6a0ab79b47f34ce924f04786.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

Recorded evaluation configuration: {"Image Backbone":"ResNet-50","Pretrain Data":"LAION","Tune On":"SARCAP"}. This record does not assert independent reproduction.

### GeoRSCLIP

R@1: 0.2. Result ID: 6a0ab79b47f34ce924f0477f.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b3c.md>)

[Implementation](<https://github.com/om-ai-lab/RS5M>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"LAION","Tune On":"RS5M"}. This record does not assert independent reproduction.

### GeoRSCLIP

R@1: 0.2. Result ID: 6a0ab79b47f34ce924f04780.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b3c.md>)

[Implementation](<https://github.com/om-ai-lab/RS5M>)

Recorded evaluation configuration: {"Image Backbone":"ViT-H-14","Pretrain Data":"LAION","Tune On":"RS5M"}. This record does not assert independent reproduction.

### SkyCLIP

R@1: 0.2. Result ID: 6a0ab79b47f34ce924f04782.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71841e209131cea51ba5.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"LAION","Tune On":"SkyScript"}. This record does not assert independent reproduction.

### SkyCLIP

R@1: 0.18. Result ID: 6a0ab79b47f34ce924f04781.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71841e209131cea51ba5.md>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"LAION","Tune On":"SkyScript"}. This record does not assert independent reproduction.

### GeoRSCLIP

R@1: 0.12. Result ID: 6a0ab79b47f34ce924f0477e.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b3c.md>)

[Implementation](<https://github.com/om-ai-lab/RS5M>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"LAION","Tune On":"RS5M"}. This record does not assert independent reproduction.

### OpenCLIP

R@1: 0.1. Result ID: 6a0ab79b47f34ce924f0477d.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74261e209131cea6003e.md>)

[Implementation](<https://github.com/LAION-AI/scaling-laws-openclip>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"LAION","Tune On":"–"}. This record does not assert independent reproduction.

### RemoteCLIP

R@1: 0.1. Result ID: 6a0ab79b47f34ce924f04784.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea596e5.md>)

[Implementation](<https://github.com/ChenDelong1999/RemoteCLIP>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"LAION","Tune On":"R3+D10+S4"}. This record does not assert independent reproduction.

### RemoteCLIP

R@1: 0.1. Result ID: 6a0ab79b47f34ce924f04785.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea596e5.md>)

[Implementation](<https://github.com/ChenDelong1999/RemoteCLIP>)

Recorded evaluation configuration: {"Image Backbone":"ViT-L-14","Pretrain Data":"LAION","Tune On":"R3+D10+S4"}. This record does not assert independent reproduction.

### OpenCLIP

R@1: 0.08. Result ID: 6a0ab79b47f34ce924f0477c.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74261e209131cea6003e.md>)

[Implementation](<https://github.com/LAION-AI/scaling-laws-openclip>)

Recorded evaluation configuration: {"Image Backbone":"ViT-B-32","Pretrain Data":"LAION","Tune On":"–"}. This record does not assert independent reproduction.

### OpenCLIP

R@1: 0.06. Result ID: 6a0ab79b47f34ce924f0477b.

[Reporting paper](<https://www.sota2.com/research/paper/69004ded3ef7ccd74e5e29e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74261e209131cea6003e.md>)

[Implementation](<https://github.com/LAION-AI/scaling-laws-openclip>)

Recorded evaluation configuration: {"Image Backbone":"ResNet-50","Pretrain Data":"LAION","Tune On":"–"}. This record does not assert independent reproduction.

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