Closed-loop planning on NAVSIM v1 (navtest)
99NCDriveLaW
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DriveLaWInput=C2026.06 | 99 | 97.1 | 96.7 | 100 | 81.3 | 89.1 | |
| DrivingGPTInput=C2026.06 | 98.9 | 90.7 | 94.9 | 95.6 | 79.7 | 82.4 | |
| DriveVLA-W0Input=C, Aux. Sup.=Future States2026.04 | 98.7 | 99.1 | 95.3 | 99.3 | 83.3 | 90.2 | |
| DVGT-2-NAVSIMInput=C, Aux. Sup.=Dense Geometry2026.04 | 98.7 | 97.9 | 95.8 | 100 | 84.3 | 90.3 | |
| DriveVLA-W0Input=C2026.06 | 98.7 | 99.1 | 95.3 | 99.3 | 83.3 | 90.2 | |
| DVGT-2-NAVSIMInput=C2026.06 | 98.7 | 97.9 | 95.8 | 100 | 84.3 | 90.3 | |
| PWMInput=C2026.06 | 98.6 | 95.9 | 95.4 | 100 | 81.8 | 88.1 | |
| LiAuto-GeoXInput=C2026.06 | 98.6 | 97.5 | 95.2 | 100 | 85.8 | 90.6 | |
| WoTEInput=C & L, Aux. Sup.=Map & Box2026.04 | 98.5 | 96.8 | 94.9 | 99.9 | 81.9 | 88.3 | |
| AdaThinkDriveInput=C, Aux. Sup.=Language2026.04 | 98.5 | 94.4 | 94.9 | 100 | 79.9 | 86.2 | |
| AdaThinkDriveInput=C2026.06 | 98.5 | 94.4 | 94.9 | 100 | 79.9 | 86.2 | |
| WoTEInput=C & L2026.06 | 98.5 | 96.8 | 94.9 | 99.9 | 81.9 | 88.3 | |
| AutoVLAInput=C, Aux. Sup.=Language & RL, Reinforcement Learning=true2026.04 | 98.4 | 95.6 | 98 | 99.9 | 85.9 | 89.1 | |
| AutoVLAInput=C2026.06 | 98.4 | 95.6 | 98 | 99.9 | 85.9 | 89.1 | |
| Hydra-MDPInput=C & L, Aux. Sup.=Map & Box2026.04 | 98.3 | 96 | 94.6 | 100 | 78.7 | 86.5 | |
| GoalFlowInput=C & L, Aux. Sup.=Map & Box2026.04 | 98.3 | 93.8 | 94.3 | 100 | 79.8 | 85.7 | |
| ARTEMISInput=C & L, Aux. Sup.=Map & Box2026.04 | 98.3 | 95.1 | 94.3 | 100 | 81.4 | 87 | |
| ReCogDriveInput=C, Aux. Sup.=Language2026.04 | 98.3 | 95.1 | 94.3 | 100 | 81.1 | 86.8 | |
| Hydra-MDPInput=C & L2026.06 | 98.3 | 96 | 94.6 | 100 | 78.7 | 86.5 | |
| GoalFlowInput=C & L2026.06 | 98.3 | 93.8 | 94.3 | 100 | 79.8 | 85.7 | |
| ARTEMISInput=C & L2026.06 | 98.3 | 95.1 | 94.3 | 100 | 81.4 | 87 | |
| VADv2Input=C2026.06 | 98.3 | 97.4 | 95.7 | 100 | 82.3 | 89.3 | |
| DiffusionDriveInput=C & L, Aux. Sup.=Map & Box2026.04 | 98.2 | 96.2 | 94.7 | 100 | 82.2 | 88.1 | |
| ReCogDriveInput=C, Aux. Sup.=Language & RL, Reinforcement Learning=true2026.04 | 98.2 | 97.8 | 95.2 | 99.8 | 83.5 | 89.6 | |
| DiffusionDriveInput=C & L2026.06 | 98.2 | 96.2 | 94.7 | 100 | 82.2 | 88.1 | |
| ReCogDriveInput=C2026.06 | 98.2 | 97.8 | 95.2 | 99.8 | 83.5 | 89.6 | |
| PARA-DriveInput=C, Aux. Sup.=Map & Mot. & Occ2026.04 | 97.9 | 92.4 | 93 | 99.8 | 79.3 | 84 | |
| EponaInput=C2026.06 | 97.9 | 95.1 | 93.8 | 99.9 | 80.4 | 86.2 | |
| UniADInput=C, Aux. Sup.=Map & Box & Mot. & Occ2026.04 | 97.8 | 91.9 | 92.9 | 100 | 78.8 | 83.4 | |
| DriveSuprimInput=C & L, Aux. Sup.=Map & Box2026.04 | 97.8 | 97.3 | 93.6 | 100 | 86.7 | 89.9 | |
| DVGT-2Input=C, Aux. Sup.=Dense Geometry2026.04 | 97.8 | 97.2 | 93.9 | 100 | 83.4 | 88.6 | |
| UniADInput=C2026.06 | 97.8 | 91.9 | 92.9 | 100 | 78.8 | 83.4 | |
| DriveSuprimInput=C & L2026.06 | 97.8 | 97.3 | 93.6 | 100 | 86.7 | 89.9 | |
| DVGT-2Input=C2026.06 | 97.8 | 97.2 | 93.9 | 100 | 83.4 | 88.6 | |
| TransfuserInput=C & L, Aux. Sup.=Map & Box2026.04 | 97.7 | 92.8 | 92.8 | 100 | 79.2 | 84 | |
| TransfuserInput=C & L2026.06 | 97.7 | 92.8 | 92.8 | 100 | 79.2 | 84 | |
| VADv2Input=C, Aux. Sup.=Map & Mot. & Traffic2026.04 | 97.2 | 89.1 | 91.6 | 100 | 76 | 80.9 | |
| AutoVLAInput=C, Aux. Sup.=Language2026.04 | 96.9 | 92.4 | 88.1 | 99.9 | 75.8 | 80.5 | |
| LAWInput=C2026.06 | 96.4 | 95.4 | 88.7 | 99.9 | 81.7 | 84.6 |