# 3D Object Detection on Waymo Open Dataset full 202 (val)

Source: [3D Object Detection on Waymo Open Dataset full 202 (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val>)

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

Data updated: 2026-02-26T05:21:16.122Z

Evaluation of 3D Object Detection performance on the validation split of the Waymo Open Dataset (full 202 configuration), reporting 3D mAP and 3D mAPH metrics broken down by distance ranges, specifically focusing on Level 1 difficulty.

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 | 3D Object Detection |
| Dataset (including any stated split) | Waymo Open Dataset full 202 (val) |
| Metric | 3D mAP L1 Overall |
| 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

- [3D mAP L1 Overall](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L1%20Overall>): Higher is better; unit: PERCENT.

- [3D mAP L1 0-30m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L1%200-30m>): Higher is better; unit: PERCENT.

- [3D mAP L1 30-50m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L1%2030-50m>): Higher is better; unit: PERCENT.

- [3D mAP L1 50m+](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L1%2050m%2B>): Higher is better; unit: PERCENT.

- [3D mAPH L1 Overall](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L1%20Overall>): Higher is better; unit: PERCENT.

- [3D mAPH L1 0-30m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L1%200-30m>): Higher is better; unit: PERCENT.

- [3D mAPH L1 30-50m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L1%2030-50m>): Higher is better; unit: PERCENT.

- [3D mAPH L1 50m+](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L1%2050m%2B>): Higher is better; unit: PERCENT.

- [3D mAP L2 Overall](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L2%20Overall>): Higher is better; unit: PERCENT.

- [3D mAP L2 0-30m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L2%200-30m>): Higher is better; unit: PERCENT.

- [3D mAP L2 30-50m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L2%2030-50m>): Higher is better; unit: PERCENT.

- [3D mAP L2 50m+](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAP%20L2%2050m%2B>): Higher is better; unit: PERCENT.

- [3D mAPH L2 Overall](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L2%20Overall>): Higher is better; unit: PERCENT.

- [3D mAPH L2 0-30m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L2%200-30m>): Higher is better; unit: PERCENT.

- [3D mAPH L2 30-50m](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L2%2030-50m>): Higher is better; unit: PERCENT.

- [3D mAPH L2 50m+](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-full-202-val.md?metric=3D%20mAPH%20L2%2050m%2B>): Higher is better; unit: PERCENT.

## Recorded results

| Method | 3D mAP L1 Overall | Result date | Report paper |
| --- | --- | --- | --- |
| M3DETR | 75.71 | Not recorded | 68fa6b191e209131cea2c28f |
| RangeDet | 72.85 | Not recorded | 68fa6b191e209131cea2c28f |
| PV-RCNN | 70.3 | Not recorded | 68fa6b191e209131cea2c28f |
| RCD | 69.59 | Not recorded | 68fa6b191e209131cea2c28f |
| PointPillars | 56.62 | Not recorded | 68fa6b191e209131cea2c28f |
| LaserNet | 52.11 | Not recorded | 68fa6b191e209131cea2c28f |

### M3DETR

3D mAP L1 Overall: 75.71. Result ID: 698e5b20ffc3901de09ce6eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c28f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c28f.md>)

[Implementation](<https://github.com/rayguan97/M3DETR>)

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

### RangeDet

3D mAP L1 Overall: 72.85. Result ID: 698e5b20ffc3901de09ce6e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c28f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69951e209131cea22d96.md>)

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

### PV-RCNN

3D mAP L1 Overall: 70.3. Result ID: 698e5b20ffc3901de09ce6ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c28f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b11e209131cea23700.md>)

[Implementation](<https://github.com/open-mmlab/OpenPCDet>)

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

### RCD

3D mAP L1 Overall: 69.59. Result ID: 698e5b20ffc3901de09ce6e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c28f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa692b1e209131cea207e2.md>)

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

### PointPillars

3D mAP L1 Overall: 56.62. Result ID: 698e5b20ffc3901de09ce6e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c28f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c01e209131cea0c2bc.md>)

[Implementation](<https://github.com/nutonomy/second.pytorch>)

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

### LaserNet

3D mAP L1 Overall: 52.11. Result ID: 698e5b20ffc3901de09ce6e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c28f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65801e209131cea0a95f.md>)

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.
