# Prompt Recovery on MS COCO Source: [Prompt Recovery on MS COCO]() Collection index: [llms.txt]() Data updated: 2026-03-06T07:08:17.900Z Evaluation of model performance on Prompt Recovery tasks using the MS COCO dataset, assessed using metrics like CLIP score, LPIPS, Precision, Recall, F1, and Perplexity (PPL). 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 | Prompt Recovery | | Dataset (including any stated split) | MS COCO | | Metric | CLIP Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [CLIP Score](): Higher is better; unit: PERCENT. - [LPIPS](): Lower is better; unit: SCALAR. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [Perplexity (PPL)](): Lower is better; unit: SCALAR. ## Recorded results | Method | CLIP Score | Result date | Report paper | | --- | --- | --- | --- | | EDITOR | 79.6 | Not recorded | 68fa791f1e209131cea7c381 | | PH2P | 78.9 | Not recorded | 68fa791f1e209131cea7c381 | | PRISM | 75.9 | Not recorded | 68fa791f1e209131cea7c381 | | PEZ | 74.5 | Not recorded | 68fa791f1e209131cea7c381 | | VGD | 72.5 | Not recorded | 68fa791f1e209131cea7c381 | | STEPS | 68.7 | Not recorded | 68fa791f1e209131cea7c381 | ### EDITOR CLIP Score: 79.6. Result ID: 69aa7c5b6dbb7075b953ba9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PH2P CLIP Score: 78.9. Result ID: 69aa7c5b6dbb7075b953ba98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PRISM CLIP Score: 75.9. Result ID: 69aa7c5b6dbb7075b953ba9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PEZ CLIP Score: 74.5. Result ID: 69aa7c5b6dbb7075b953ba97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VGD CLIP Score: 72.5. Result ID: 69aa7c5b6dbb7075b953ba99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### STEPS CLIP Score: 68.7. Result ID: 69aa7c5b6dbb7075b953ba9a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.