# Object Detection on COCO Open-vocabulary v1 Source: [Object Detection on COCO Open-vocabulary v1]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:53:57.695Z Evaluation of Object Detection performance on the COCO Open-vocabulary v1 dataset, utilizing metrics that distinguish between known and novel object categories (Novel AP, Known AP). 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 | Object Detection | | Dataset (including any stated split) | COCO Open-vocabulary v1 | | Metric | Novel AP | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 0 of 0 | | 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 - [Novel AP](): Higher is better; unit: PERCENT. - [Novel AP@50](): Higher is better; unit: PERCENT. - [Known AP](): Higher is better; unit: PERCENT. - [Known AP@50](): Higher is better; unit: PERCENT. - [All AP](): Higher is better; unit: PERCENT. - [All AP@50](): Higher is better; unit: PERCENT. - [Base AP](): Higher is better; unit: PERCENT. ## Recorded results | Method | Novel AP | Result date | Report paper | | --- | --- | --- | --- | Page 1 of 1. This is an index page, not the full collection.