# Text-to-image Retrieval on MS COCO (R@K, MdR) Source: [Text-to-image Retrieval on MS COCO (R@K, MdR)]() Collection index: [llms.txt]() Data updated: 2026-05-15T09:06:26.601Z Evaluation of Text-to-Image Retrieval performance on the MS COCO dataset, reporting Recall@K metrics (R@1, R@5, R@10) and Median Rank (MdR). 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) | MS COCO | | Metric | R@1 | | Unit | PERCENT | | 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 - [R@1](): Higher is better; unit: PERCENT. - [R@5](): Higher is better; unit: PERCENT. - [R@10](): Higher is better; unit: PERCENT. - [MdR](): Lower is better; unit: SCALAR. ## Recorded results | Method | R@1 | Result date | Report paper | | --- | --- | --- | --- | | OpenCLIP-RN50 | 97.6 | Not recorded | 68fa7b191e209131cea868ca | | ImageBind | 85.1 | Not recorded | 68fa7b191e209131cea868ca | | OpenCLIP-ViT | 84.4 | Not recorded | 68fa7b191e209131cea868ca | | AudioCLIP | 62 | Not recorded | 68fa7b191e209131cea868ca | | OpenCLIP-ViT | 48.5 | Not recorded | 68fa7b191e209131cea868ca | | ImageBind | 48.4 | Not recorded | 68fa7b191e209131cea868ca | | OpenCLIP-RN50 | 28.3 | Not recorded | 68fa7b191e209131cea868ca | | AudioCLIP | 18.8 | Not recorded | 68fa7b191e209131cea868ca | | OpenCLIP-ViT | 11.3 | Not recorded | 68fa7b191e209131cea868ca | | ImageBind | 10.9 | Not recorded | 68fa7b191e209131cea868ca | | AudioCLIP | 8.8 | Not recorded | 68fa7b191e209131cea868ca | | OpenCLIP-RN50 | 1.4 | Not recorded | 68fa7b191e209131cea868ca | ### OpenCLIP-RN50 R@1: 97.6. Result ID: 6a06e20347f34ce924eebcdd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Adv. Hub."}. This record does not assert independent reproduction. ### ImageBind R@1: 85.1. Result ID: 6a06e20347f34ce924eebcd4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Adv. Hub."}. This record does not assert independent reproduction. ### OpenCLIP-ViT R@1: 84.4. Result ID: 6a06e20347f34ce924eebcda. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Adv. Hub."}. This record does not assert independent reproduction. ### AudioCLIP R@1: 62. Result ID: 6a06e20347f34ce924eebcd7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Adv. Hub."}. This record does not assert independent reproduction. ### OpenCLIP-ViT R@1: 48.5. Result ID: 6a06e20347f34ce924eebcd8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Clean","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. ### ImageBind R@1: 48.4. Result ID: 6a06e20347f34ce924eebcd2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Clean","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. ### OpenCLIP-RN50 R@1: 28.3. Result ID: 6a06e20347f34ce924eebcdb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Clean","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. ### AudioCLIP R@1: 18.8. Result ID: 6a06e20347f34ce924eebcd5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Clean","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. ### OpenCLIP-ViT R@1: 11.3. Result ID: 6a06e20347f34ce924eebcd9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. ### ImageBind R@1: 10.9. Result ID: 6a06e20347f34ce924eebcd3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. ### AudioCLIP R@1: 8.8. Result ID: 6a06e20347f34ce924eebcd6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. ### OpenCLIP-RN50 R@1: 1.4. Result ID: 6a06e20347f34ce924eebcdc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Gallery":"Poisoned","Retrieved":"Relevant Doc."}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.