| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| nuScenes (val) | Ours-0.5B | L2 Error (3s)0.1 | 225 | 2mo ago | |
| nuScenes | OWMDrive | L2 Error (Avg)0.18 | 130 | 25d ago | |
| nuScenes v1.0-trainval (val) | FSDrive | L2 Error (Avg)0.28 | 84 | 1mo ago | |
| nuScenes v1.0 (test) | Senna | L2 Error (1s)0.11 | 84 | 1mo ago | |
| nuScenes v1.0 (val) | Senna | L2 (1s)0.11 | 71 | 3mo ago | |
| Bench2Drive | DriveMOE | Average L2 Error0.38 | 47 | 3mo ago | |
| nuScenes open-loop evaluation | EMMA+ | L2 Error (1s) (m)0.13 | 18 | 3mo ago | |
| Waymo | BEVPlaner++ | L2 Error (1s)0.21 | 16 | 2mo ago | |
| NAVSIM | HEAT | L2 Error (1s Horizon)0.07 | 16 | 2mo ago | |
| Bench2Drive base set open-loop | GeRo (ORION) | Average L2 Error0.57 | 15 | 4mo ago | |
| Bench2Drive base V0.0.3 (train) | DriveTrans | Avg L2 Error0.62 | 12 | 1mo ago | |
| nuPlan 14 (val) | OLS100 | 9 | 4mo ago | ||
| NAVSIM v2 (navtest) | NC100 | 8 | 1mo ago | ||
| nuPlan (test) | KnowDiffuser | ADE (8s)0.298 | 8 | 4mo ago | |
| Turning-nuScenes (val) | MomAD | L2 Error (1s)0.33 | 8 | 4mo ago | |
| WOMD | GameFormer | Collision Rate1.98 | 8 | 4mo ago | |
| Bench2Drive (test) | UniAD-Base | Avg L2 Error (m)0.73 | 8 | 4mo ago | |
| nuPlan (rare) | PDMS62.69 | 7 | 1mo ago | ||
| nuPlan common | World Engine | PDMS88.95 | 7 | 1mo ago | |
| Bench2Drive V0.0.3 | MomAD | Avg L2 Error0.82 | 7 | 4mo ago | |
| Bench2Drive (val) | UniDrive-WM | L2 Error (1s)0.247 | 5 | 4mo ago | |
| NAVSIM | Hydra-MDP | NC98.3 | 4 | 4mo ago |