Motion Planning on NAVSIM v1 (test)
100NCHuman Agent
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Human AgentSensors=N/A2026.06 | 100 | 100 | 87.5 | 100 | 99.9 | 94.8 | |
| DriveLAWSensors=1xC, Strategy=Training on full navtrain split2026.06 | 99 | 97.1 | 81.3 | 96.7 | 100 | 89.1 | |
| VegaSensors=1xC2026.06 | 98.9 | 95.3 | 81.6 | 96.1 | 100 | 87.9 | |
| Drive-JEPASensors=1xC2026.06 | 98.7 | 96.2 | 82.9 | 100 | 95.5 | 89 | |
| DriveVLA-W0Sensors=1xC, Strategy=Training on full navtrain split2026.06 | 98.7 | 96.2 | 82.2 | 95.5 | 100 | 88.4 | |
| UniWorldVLASensors=1xC, Strategy=Training on full navtrain split2026.06 | 98.7 | 96.7 | 83.2 | 96.1 | 100 | 89.4 | |
| SGDrive-ILSensors=1xC, Strategy=Imitation Learning2026.06 | 98.6 | 95.1 | 81.2 | 95.4 | 100 | 87.4 | |
| ImagiDriveSensors=1xC2026.06 | 98.6 | 96.2 | 80.5 | 94.5 | 100 | 87.4 | |
| PWMSensors=1xC, Strategy=Training on full navtrain split2026.06 | 98.6 | 95.9 | 81.8 | 95.4 | 100 | 88.1 | |
| WoTESensors=3xC+L2026.06 | 98.5 | 96.8 | 81.9 | 94.9 | 99.9 | 88.3 | |
| MetisSensors=1xC, Strategy=best-of-N (N = 6)2026.06 | 98.5 | 97.5 | 84 | 95.1 | 100 | 89.7 | |
| WorldDriveSensors=1xC2026.06 | 98.4 | 96.2 | 81.9 | 95.1 | 100 | 88.1 | |
| SeerDriveSensors=3/6xC+L2026.06 | 98.4 | 97 | 83.2 | 94.9 | 99.9 | 88.9 | |
| ARTEMISSensors=3xC+L2026.06 | 98.3 | 95.1 | 81.4 | 94.3 | 100 | 87 | |
| MetisSensors=1xC2026.06 | 98.3 | 97.1 | 83.4 | 94.7 | 100 | 89.1 | |
| DiffusionDriveSensors=3xC+L2026.06 | 98.2 | 96.2 | 82.2 | 94.7 | 100 | 88.1 | |
| ReCogDrive-ILSensors=1xC, Strategy=Imitation Learning2026.06 | 98.1 | 94.7 | 80.9 | 94.2 | 100 | 86.5 | |
| DRAMASensors=3xC+L2026.06 | 98 | 93.1 | 80.1 | 94.8 | 100 | 85.5 | |
| PARA-DriveSensors=6xC2026.06 | 97.9 | 92.4 | 79.3 | 93 | 99.8 | 84 | |
| EponaSensors=1xC2026.06 | 97.9 | 95.1 | 80.4 | 93.8 | 99.9 | 86.2 | |
| UniADSensors=6xC2026.06 | 97.8 | 91.9 | 78.8 | 92.9 | 100 | 83.4 | |
| TransFuserSensors=3xC+L2026.06 | 97.7 | 92.8 | 79.2 | 92.8 | 100 | 84 | |
| Hydra-MDP++Sensors=3xC+L2026.06 | 97.6 | 96 | 80.4 | 93.1 | 100 | 86.6 | |
| WorldRFTSensors=3xC, Training=Reinforcement Learning2026.06 | 97.5 | 96 | 80.9 | 94 | 100 | 87 | |
| World4DriveSensors=3xC2026.06 | 97.4 | 94.3 | 79.9 | 92.8 | 100 | 85.1 | |
| AutoVLA-ILSensors=3xC, Strategy=Imitation Learning2026.06 | 96.9 | 92.4 | 75.8 | 88.1 | 99.1 | 80.5 | |
| LAWSensors=1xC2026.06 | 96.4 | 95.4 | 81.7 | 88.7 | 99.9 | 84.6 |