# 2D Object Detection on Waymo Open Dataset Real-time 2D Detection track (test)

Source: [2D Object Detection on Waymo Open Dataset Real-time 2D Detection track (test)](<https://www.sota2.com/research/sota/2d-object-detection-on-waymo-open-dataset-real-time-2d-detection-track-test>)

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

Data updated: 2026-02-26T05:23:06.885Z

Evaluation of 2D Object Detection performance on the test split of the Waymo Open Dataset's Real-time 2D Detection track, reporting AP metrics and latency.

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 | 2D Object Detection |
| Dataset (including any stated split) | Waymo Open Dataset Real-time 2D Detection track (test) |
| Metric | AP (L1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [AP (L1)](<https://www.sota2.com/research/sota/2d-object-detection-on-waymo-open-dataset-real-time-2d-detection-track-test.md?metric=AP%20(L1)>): Higher is better; unit: PERCENT.

- [AP (L2)](<https://www.sota2.com/research/sota/2d-object-detection-on-waymo-open-dataset-real-time-2d-detection-track-test.md?metric=AP%20(L2)>): Higher is better; unit: PERCENT.

- [Latency (s)](<https://www.sota2.com/research/sota/2d-object-detection-on-waymo-open-dataset-real-time-2d-detection-track-test.md?metric=Latency%20(s)>): Lower is better; unit: TIME.

## Recorded results

| Method | AP (L1) | Result date | Report paper |
| --- | --- | --- | --- |
| LeapMotor\_Det | 75.71 | Not recorded | 68fa6a261e209131cea265b8 |
| YOLOR\_TensorRT | 75 | Not recorded | 68fa6a261e209131cea265b8 |
| YOLOR\_P6\_TRT | 74.84 | Not recorded | 68fa6a261e209131cea265b8 |
| dereyly\_self\_ensemble | 71.73 | Not recorded | 68fa6a261e209131cea265b8 |
| YOLO\_v5 | 70.25 | Not recorded | 68fa6a261e209131cea265b8 |

### LeapMotor\_Det

AP (L1): 75.71. Result ID: 698e1714ffc3901de09ab8a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265b8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### YOLOR\_TensorRT

AP (L1): 75. Result ID: 698e1714ffc3901de09ab8a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265b8.md>)

Recorded evaluation configuration: {"Optimization":"TensorRT"}. This record does not assert independent reproduction.

### YOLOR\_P6\_TRT

AP (L1): 74.84. Result ID: 698e1714ffc3901de09ab8a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265b8.md>)

Recorded evaluation configuration: {"Model Variant":"P6","Optimization":"TensorRT"}. This record does not assert independent reproduction.

### dereyly\_self\_ensemble

AP (L1): 71.73. Result ID: 698e1714ffc3901de09ab8a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265b8.md>)

Recorded evaluation configuration: {"strategy":"self\_ensemble"}. This record does not assert independent reproduction.

### YOLO\_v5

AP (L1): 70.25. Result ID: 698e1714ffc3901de09ab8a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265b8.md>)

Recorded evaluation configuration: {"Model Variant":"v5"}. This record does not assert independent reproduction.

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