Autonomous Driving Planning on Nav (test)
100NCHuman
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Human2026.04 | 100 | 100 | 100 | 99.9 | 87.5 | 94.8 | — | — | — | — | — | — | |
| Human AgentBackbone=N/A, H-Demo=N/A2025.10 | 100 | 100 | 100 | — | 87.4 | — | 99.8 | 100 | 100 | 98.1 | 90.1 | 90.3 | |
| GTRS-DenseBackbone=ViT-L, H-Demo=true2025.10 | 99 | 97.8 | 98.3 | — | 86.3 | — | 99.3 | 99.9 | 95.1 | 98.3 | 71.9 | 84.7 | |
| HydraMDP++Backbone=ViT-L, H-Demo=true2025.10 | 98.5 | 98.5 | 97.9 | — | 87.4 | — | 99.5 | 99.7 | 95.8 | 98.2 | 75.7 | 85.6 | |
| DriveSuprimBackbone=ViT-L, H-Demo=true2025.10 | 98.4 | 98.6 | 97.8 | — | 90.5 | — | 99.6 | 99.8 | 97 | 98.3 | 78.6 | 87.1 | |
| HydraMDP++Backbone=V2-99, H-Demo=true2025.10 | 98.4 | 98 | 97.7 | — | 87.5 | — | 99.4 | 99.8 | 95.3 | 98.3 | 77.4 | 85.1 | |
| Hydra-MDPPlanning=Reactive, Future Reasoning Mechanism=Model-free Reranking2026.04 | 98.3 | 96 | 94.6 | 100 | 78.7 | 86.5 | — | — | — | — | — | — | |
| FSDrivePlanning=Proactive, Future Reasoning Mechanism=Visual Spatio-Temporal CoT2026.04 | 98.2 | 93.8 | 93.3 | 99.9 | 80.1 | 85.1 | — | — | — | — | — | — | |
| ZTRSBackbone=ViT-L, H-Demo=false2025.10 | 98.2 | 99.1 | 97.5 | — | 86.9 | — | 99.7 | 99.8 | 96.6 | 98.2 | 78.2 | 86.2 | |
| DRAMAPlanning=Reactive2026.04 | 98 | 93.1 | 94.8 | 100 | 80.1 | 85.5 | — | — | — | — | — | — | |
| ProDrivePlanning=Proactive, Future Reasoning Mechanism=World-model Reranking2026.04 | 98 | 95.4 | 93.7 | 99.9 | 80.7 | 86.6 | — | — | — | — | — | — | |
| VADv2Planning=Reactive, Future Reasoning Mechanism=Rule-based Reranking2026.04 | 97.9 | 91.7 | 92.9 | 100 | 77.6 | 83 | — | — | — | — | — | — | |
| PARA-DrivePlanning=Reactive, Future Reasoning Mechanism=Rule-based Constraints2026.04 | 97.9 | 92.4 | 93 | 99.8 | 79.3 | 84 | — | — | — | — | — | — | |
| EponaPlanning=Reactive, Future Reasoning Mechanism=World-model Joint Training2026.04 | 97.9 | 95.1 | 93.8 | 99.9 | 80.4 | 86.2 | — | — | — | — | — | — | |
| ZTRSBackbone=ResNet34, H-Demo=false2025.10 | 97.9 | 98 | 96.9 | — | 80.1 | — | 99.7 | 99.8 | 94.9 | 98.1 | 79 | 83.2 | |
| UniADPlanning=Reactive, Future Reasoning Mechanism=Rule-based Constraints2026.04 | 97.8 | 91.9 | 92.9 | 100 | 78.8 | 83.4 | — | — | — | — | — | — | |
| DriveSuprimBackbone=V2-99, H-Demo=true2025.10 | 97.8 | 97.9 | 97.1 | — | 90.6 | — | 99.5 | 99.9 | 96.6 | 98.3 | 77.9 | 86 | |
| ZTRSBackbone=V2-99, H-Demo=false2025.10 | 97.8 | 99.4 | 97 | — | 84.1 | — | 99.8 | 99.8 | 96.2 | 98.2 | 77.2 | 85.3 | |
| TransFuserPlanning=Reactive2026.04 | 97.7 | 92.8 | 92.8 | 100 | 79.2 | 84 | — | — | — | — | — | — | |
| GTRS-DenseBackbone=V2-99, H-Demo=true2025.10 | 97.6 | 98.5 | 97.2 | — | 89.5 | — | 99.5 | 99.9 | 96.8 | 97.2 | 57.2 | 84 | |
| DriveSuprimBackbone=ResNet34, H-Demo=true2025.10 | 97.5 | 96.5 | 96.6 | — | 88.4 | — | 99.4 | 99.6 | 95.5 | 98.3 | 77 | 83.1 | |
| LTFPlanning=Reactive2026.04 | 97.4 | 92.8 | 92.4 | 100 | 79 | 83.8 | — | — | — | — | — | — | |
| World4DrivePlanning=Reactive, Future Reasoning Mechanism=World-model Reranking2026.04 | 97.4 | 94.3 | 92.8 | 100 | 79.9 | 85.1 | — | — | — | — | — | — | |
| HydraMDP++Backbone=ResNet34, H-Demo=true2025.10 | 97.2 | 97.5 | 96.5 | — | 83.1 | — | 99.4 | 99.6 | 94.4 | 98.2 | 70.9 | 81.4 | |
| TransfuserBackbone=ResNet34, H-Demo=true2025.10 | 96.9 | 89.9 | 95.4 | — | 87.1 | — | 97.8 | 99.7 | 92.7 | 98.3 | 87.2 | 76.7 | |
| LAWPlanning=Proactive, Future Reasoning Mechanism=World-model Joint Training2026.04 | 96.4 | 95.4 | 88.7 | 99.9 | 81.7 | 84.6 | — | — | — | — | — | — | |
| Ego Status MLPBackbone=N/A, H-Demo=true2025.10 | 93.1 | 77.9 | 91.5 | — | 86 | — | 92.7 | 99.6 | 89.4 | 98.3 | 85.4 | 64 | |
| AD-MLPPlanning=Reactive2026.04 | 93 | 77.3 | 83.6 | 100 | 62.8 | 65.6 | — | — | — | — | — | — |