# Image-Text Retrieval on Flickr30k (NDCG@5)

Source: [Image-Text Retrieval on Flickr30k (NDCG@5)](<https://www.sota2.com/research/sota/image-text-retrieval-on-flickr30k-ndcg-at-5>)

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

Data updated: 2026-04-21T12:18:06.299Z

Evaluation of bidirectional Image-Text Retrieval performance on the Flickr30k dataset, reporting Normalized Discounted Cumulative Gain at 5 (NDCG@5).

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-Text Retrieval |
| Dataset (including any stated split) | Flickr30k |
| Metric | NDCG@5 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [NDCG@5](<https://www.sota2.com/research/sota/image-text-retrieval-on-flickr30k-ndcg-at-5.md?metric=NDCG%405>): Higher is better; unit: SCALAR.

- [NDCG@5 Drop (%)](<https://www.sota2.com/research/sota/image-text-retrieval-on-flickr30k-ndcg-at-5.md?metric=NDCG%405%20Drop%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | NDCG@5 | Result date | Report paper |
| --- | --- | --- | --- |
| HONES (tuned) | 0.898 | Not recorded | 69e704d47d0172140ec7efea |
| HONES (zero-shot) | 0.892 | Not recorded | 69e704d47d0172140ec7efea |
| RandNeuron | 0.889 | Not recorded | 69e704d47d0172140ec7efea |
| Base | 0.888 | Not recorded | 69e704d47d0172140ec7efea |
| HONES (tuned) | 0.883 | Not recorded | 69e704d47d0172140ec7efea |
| HONES (zero-shot) | 0.87 | Not recorded | 69e704d47d0172140ec7efea |
| RandNeuron | 0.864 | Not recorded | 69e704d47d0172140ec7efea |
| Base | 0.863 | Not recorded | 69e704d47d0172140ec7efea |

### HONES (tuned)

NDCG@5: 0.898. Result ID: 69e76af147f34ce924cef6cb.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction.

### HONES (zero-shot)

NDCG@5: 0.892. Result ID: 69e76af147f34ce924cef6c9.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction.

### RandNeuron

NDCG@5: 0.889. Result ID: 69e76af147f34ce924cef6ca.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction.

### Base

NDCG@5: 0.888. Result ID: 69e76af147f34ce924cef6c8.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction.

### HONES (tuned)

NDCG@5: 0.883. Result ID: 69e76af147f34ce924cef6c7.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

### HONES (zero-shot)

NDCG@5: 0.87. Result ID: 69e76af147f34ce924cef6c5.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

### RandNeuron

NDCG@5: 0.864. Result ID: 69e76af147f34ce924cef6c6.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

### Base

NDCG@5: 0.863. Result ID: 69e76af147f34ce924cef6c4.

[Reporting paper](<https://www.sota2.com/research/paper/69e704d47d0172140ec7efea.md>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

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