# VLM High-level Planning on nuScenes (val)

Source: [VLM High-level Planning on nuScenes (val)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val>)

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

Data updated: 2026-03-17T08:00:09.991Z

Evaluation of high-level planning performance using VLM-specific metrics (Planning Accuracy and maneuver-specific F1 scores) on the nuScenes validation set.

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 | VLM High-level Planning |
| Dataset (including any stated split) | nuScenes (val) |
| Metric | Planning Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Planning Accuracy](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Planning%20Accuracy>): Higher is better; unit: PERCENT.

- [Path F1 (Go Straight)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Path%20F1%20(Go%20Straight)>): Higher is better; unit: PERCENT.

- [Path F1 (Turn Left)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Path%20F1%20(Turn%20Left)>): Higher is better; unit: PERCENT.

- [Path F1 (Turn Right)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Path%20F1%20(Turn%20Right)>): Higher is better; unit: PERCENT.

- [Speed F1 (Keep)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Speed%20F1%20(Keep)>): Higher is better; unit: PERCENT.

- [Speed F1 (Accelerate)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Speed%20F1%20(Accelerate)>): Higher is better; unit: PERCENT.

- [Speed F1 (Decelerate)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Speed%20F1%20(Decelerate)>): Higher is better; unit: PERCENT.

- [Speed F1 (Stop)](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=Speed%20F1%20(Stop)>): Higher is better; unit: PERCENT.

- [FPS](<https://www.sota2.com/research/sota/vlm-high-level-planning-on-nuscenes-val.md?metric=FPS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Planning Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FlowAD | 90.99 | Not recorded | 69b8e00a0636e5bf4afbea03 |
| Senna | 88.54 | Not recorded | 69b8e00a0636e5bf4afbea03 |
| Senna | 18.67 | Not recorded | 69b8e00a0636e5bf4afbea03 |

### FlowAD

Planning Accuracy: 90.99. Result ID: 69b9099747f34ce924a159f3.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00a0636e5bf4afbea03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e00a0636e5bf4afbea03.md>)

Recorded evaluation configuration: {"Finetuned on nuScenes":"true"}. This record does not assert independent reproduction.

### Senna

Planning Accuracy: 88.54. Result ID: 69b9099747f34ce924a159f2.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00a0636e5bf4afbea03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75771e209131cea68209.md>)

Recorded evaluation configuration: {"Finetuned on nuScenes":"true"}. This record does not assert independent reproduction.

### Senna

Planning Accuracy: 18.67. Result ID: 69b9099747f34ce924a159f1.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00a0636e5bf4afbea03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75771e209131cea68209.md>)

Recorded evaluation configuration: {"Finetuned on nuScenes":"false"}. This record does not assert independent reproduction.

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