Planning on nuPlan 14 (val)
93.53Overall ScoreLog-replay
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Log-replayType=Expert, Evaluation Protocol=Non-reactive (NR)2026.06 | 93.53 | — | — | |
| DFP (ours) †Type=Learning-based, Evaluation Protocol=Non-reactive (NR), components=Flow Matching + Mixture-of-Transformer2026.06 | 92.68 | — | — | |
| Flow PlannerType=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 90.43 | — | — | |
| DFP (ours)Type=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 90.33 | — | — | |
| Diffusion PlannerType=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 89.87 | — | — | |
| CoPlannerType=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 89.48 | — | — | |
| PLUTOType=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 88.89 | — | — | |
| Diffusion Planner *Type=Learning-based, Evaluation Protocol=Non-reactive (NR), reproduced=true2026.06 | 87.87 | — | — | |
| PlanTFType=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 84.27 | — | — | |
| Flow PlannerType=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 83.31 | — | — | |
| Diffusion PlannerType=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 82.8 | — | — | |
| DFP (ours) †Type=Learning-based, Evaluation Protocol=Reactive (R), components=Flow Matching + Mixture-of-Transformer2026.06 | 81.3 | — | — | |
| Log-replayType=Expert, Evaluation Protocol=Reactive (R)2026.06 | 80.32 | — | — | |
| DFP (ours)Type=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 79.97 | — | — | |
| CoPlannerType=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 79 | — | — | |
| PLUTOType=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 78.11 | — | — | |
| Diffusion Planner *Type=Learning-based, Evaluation Protocol=Reactive (R), reproduced=true2026.06 | 77.48 | — | — | |
| PlanTFType=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 76.95 | — | — | |
| UrbanDriverType=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 68.57 | — | — | |
| UrbanDriverType=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 64.11 | — | — | |
| PDM-Open*Type=Learning-based, Evaluation Protocol=Reactive (R), reproduced=true2026.06 | 54.24 | — | — | |
| PDM-Open*Type=Learning-based, Evaluation Protocol=Non-reactive (NR), reproduced=true2026.06 | 53.53 | — | — | |
| GameFormerType=Learning-based, Evaluation Protocol=Non-reactive (NR)2026.06 | 13.32 | — | — | |
| GameFormerType=Learning-based, Evaluation Protocol=Reactive (R)2026.06 | 8.69 | — | — | |
| BIBeRIntegration=Co-Leader2025.12 | — | 90.07 | 89.79 | |
| BIBeR-CVIntegration=Co-Leader2025.12 | — | 91.92 | 92.75 | |
| DiffusionPlannerIntegration=Joint2025.12 | — | 89.87 | 82.8 | |
| DTPPIntegration=Co-Leader2025.12 | — | 71.66 | 66.09 | |
| GameFormerIntegration=Joint2025.12 | — | 79.94 | 79.78 | |
| GC-PGPIntegration=None2025.12 | — | 58.4 | 63.82 | |
| PDM-ClosedIntegration=Human Leader2025.12 | — | 92.84 | 92.12 | |
| PDM-HybridIntegration=Human Leader2025.12 | — | 92.77 | 92.11 | |
| PDM-OpenIntegration=None2025.12 | — | 53.53 | 54.24 | |
| PlanCNNIntegration=None2025.12 | — | 73 | 72 | |
| PlanTFIntegration=None2025.12 | — | 84.27 | 76.95 | |
| Urban DriverIntegration=None2025.12 | — | 68.57 | 64.11 |