nuScenes: Results as Published

nuScenes is a driving dataset for detecting and tracking objects around a vehicle. It has 1,000 scenes, each 20 seconds long, from 6 cameras, 5 radars, and 1 lidar, all with a full 360 degree field of view. Every scene is annotated with 3D bounding boxes for 23 classes and 8 attributes. The paper defines its own 3D detection and tracking metrics for those boxes, but it does not print the metric formulas in the abstract.

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.