Planning on Navsim v2 (navtest)
98.9NCFlowR2A
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| FlowR2AImg. Backbone=ResNet-342026.06 | 98.9 | 98.1 | 99.1 | 99.7 | 91.5 | 98.5 | 95 | 98.3 | 65.2 | 88.9 | |
| DriveFutureMethod Category=World-Model-based Methods2026.05 | 98.8 | 99.1 | 99.6 | 99.9 | 86.6 | 98.4 | 96.4 | 98.3 | 74.8 | 86.4 | |
| DriveWorld-VLAMethod Category=VLA-based Methods2026.05 | 98.6 | 99.1 | 99.6 | 99.8 | 87.4 | 97.9 | 97 | 97.8 | 78.6 | 86.8 | |
| DriveVLA-W0Venue=ICLR’26, Category=Vision-Language-Action Methods2026.04 | 98.5 | 99.1 | 98 | 99.7 | 86.4 | 98.1 | 93.2 | 97.9 | 58.9 | 86.1 | |
| DriveVLA-W0Method Category=VLA-based Methods2026.05 | 98.5 | 99.1 | 98 | 99.7 | 86.4 | 98.1 | 93.2 | 97.9 | 58.9 | 86.1 | |
| DriveDreamer-PolicyVenue=None, Category=World-Model-Based Methods2026.04 | 98.4 | 97.1 | 99.5 | 99.9 | 87.9 | 97.7 | 97.6 | 98.3 | 79.4 | 88.7 | |
| Hydra-MDP++Img. Backbone=V2-992026.06 | 98.4 | 98 | 99.4 | 99.8 | 87.5 | 97.7 | 95.3 | 98.3 | 77.4 | 85.1 | |
| ARTEMISVenue=RAL’26, Category=Vision-Based End-to-End Methods2026.04 | 98.3 | 95.1 | 98.6 | 99.8 | 81.5 | 97.4 | 96.5 | 98.3 | 89.1 | 83.1 | |
| ARTEMISMethod Category=E2E-based Methods2026.05 | 98.3 | 95.1 | 98.6 | 99.8 | 81.5 | 97.4 | 96.5 | 98.3 | 98.3 | 83.1 | |
| RecogdriveMethod Category=VLA-based Methods2026.05 | 98.3 | 95.2 | 98.3 | 99.8 | 87.1 | 97.5 | 96.6 | 99.5 | 86.5 | 83.6 | |
| ARTEMIS2025.07 | 98.3 | 95.1 | 98.6 | 99.8 | 81.5 | 97.4 | 96.5 | 98.3 | — | 83.1 | |
| ARTEMISImg. Backbone=ResNet-342026.06 | 98.3 | 95.1 | 98.6 | 99.8 | 81.5 | 97.4 | 96.5 | 98.3 | — | 83.1 | |
| DiffusionDriveVenue=CVPR’25, Category=Vision-Based End-to-End Methods2026.04 | 98.2 | 95.9 | 99.4 | 99.8 | 87.5 | 97.3 | 96.8 | 98.3 | 87.7 | 84.5 | |
| DiffusionDriveMethod Category=E2E-based Methods2026.05 | 98.2 | 95.9 | 99.4 | 99.8 | 87.5 | 97.3 | 96.8 | 98.3 | 87.7 | 84.5 | |
| Latent-WAMMethod Category=World-Model-based Methods2026.05 | 98.1 | 97.3 | 99.6 | 99.8 | 87.7 | 97.3 | 97.6 | 98.1 | 87.3 | 89.3 | |
| DriveSuprimImg. Backbone=V2-992026.06 | 97.8 | 97.9 | 99.5 | 99.9 | 90.6 | 97.1 | 96.6 | 98.3 | 77.9 | 86 | |
| DiffusionDriveV2Method Category=E2E-based Methods2026.05 | 97.7 | 96.6 | 99.2 | 99.8 | 88.9 | 97.2 | 96 | 97.8 | 91 | 85.5 | |
| DiffusionDriveV22025.07 | 97.7 | 96.6 | 99.2 | 99.8 | 88.9 | 97.2 | 96 | 97.8 | 91 | 85.5 | |
| DrivesuprimVenue=AAAI’26, Category=Vision-Based End-to-End Methods2026.04 | 97.5 | 96.5 | 99.4 | 99.6 | 88.4 | 96.6 | 95.5 | 98.3 | 77 | 83.1 | |
| DriveSuprimMethod Category=E2E-based Methods2026.05 | 97.5 | 96.5 | 99.4 | 99.6 | 88.4 | 96.6 | 95.5 | 98.3 | 77 | 83.1 | |
| DriveSuprim2025.07 | 97.5 | 96.5 | 99.4 | 99.6 | 88.4 | 96.6 | 95.5 | 98.3 | 77 | 83.1 | |
| DIVER2025.07 | 97.5 | 95 | 98.3 | 99.8 | 87.8 | 95.9 | 93 | 98.5 | 87.7 | 82.2 | |
| DriveSuprimImg. Backbone=ResNet-342026.06 | 97.5 | 96.5 | 99.4 | 99.6 | 88.4 | 96.6 | 95.5 | 98.3 | 77 | 83.1 | |
| Hydra-MDP++Method Category=E2E-based Methods2026.05 | 97.2 | 97.5 | 99.4 | 99.6 | 83.1 | 96.5 | 94.4 | 98.2 | 70.9 | 81.4 | |
| Hydra-MDP++2025.07 | 97.2 | 97.5 | 99.4 | 99.6 | 83.1 | 96.5 | 94.4 | 98.2 | 70.9 | 81.4 | |
| Hydra-MDP++Img. Backbone=ResNet-342026.06 | 97.2 | 97.5 | 99.4 | 99.6 | 83.1 | 96.5 | 94.4 | 98.2 | 70.9 | 81.4 | |
| TransFuservariant=multi-mode trajectory, re-implementation=true2025.07 | 97 | 90.1 | 97.6 | 99.5 | 87.3 | 95.5 | 92.4 | 98.2 | 87.3 | 76.9 | |
| TransFuserVenue=TPAMI’23, Category=Vision-Based End-to-End Methods2026.04 | 96.9 | 89.9 | 97.8 | 99.7 | 87.1 | 95.4 | 92.7 | 98.3 | 87.2 | 76.7 | |
| TransFuserMethod Category=E2E-based Methods2026.05 | 96.9 | 89.9 | 97.8 | 99.7 | 87.1 | 95.4 | 92.7 | 98.3 | 87.2 | 76.7 | |
| TransFuser2025.07 | 96.9 | 89.9 | 97.8 | 99.7 | 87.1 | 95.4 | 92.7 | 98.3 | 87.2 | 76.7 | |
| TransfuserImg. Backbone=ResNet-342026.06 | 96.9 | 89.9 | 97.8 | 99.7 | 87.1 | 95.4 | 92.7 | 98.3 | 87.2 | 76.7 | |
| Ego Status MLPImg. Backbone=ResNet-342026.06 | 93.1 | 77.9 | 92.7 | 99.6 | 86 | 91.5 | 89.4 | 98.3 | 85.4 | 64 |