End-to-End Autonomous Driving on Bench2Drive v1.0 (Full-data)
86.86Driving ScoreDeLL
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| DeLLProtocol=Full-data learning2026.03 | 86.86 | 68.63 | 61.25 | 62.22 | 80 | 60 | 81.05 | 68.9 | |
| HiP-ADProtocol=Full-data learning2026.03 | 86.77 | 69.09 | 50 | 84.44 | 83.33 | 40 | 72.1 | 65.98 | |
| SimLingoProtocol=Full-data learning2026.03 | 85.07 | 67.27 | 54.01 | 57.04 | 88.33 | 53.33 | 82.45 | 67.03 | |
| TF++Protocol=Full-data learning2026.03 | 84.21 | 67.27 | 58.75 | 57.77 | 83.33 | 40 | 82.11 | 64.39 | |
| ORIONProtocol=Full-data learning2026.03 | 77.74 | 54.62 | 25 | 71.11 | 78.33 | 30 | 69 | 54.72 | |
| DriveMoEProtocol=Full-data learning2026.03 | 74.22 | 48.64 | 34.67 | 40 | 65.45 | 40 | 59.44 | 47.91 | |
| DiffADProtocol=Full-data learning2026.03 | 67.92 | 38.64 | 30 | 35.55 | 46.66 | 40 | 46.32 | 38.79 | |
| DriveAdapterProtocol=Full-data learning2026.03 | 64.22 | 33.08 | 28.82 | 26.38 | 48.76 | 50 | 56.43 | 42.08 | |
| DriveTransformerProtocol=Full-data learning2026.03 | 63.46 | 35.01 | 17.57 | 35 | 48.36 | 40 | 52.1 | 38.6 | |
| ThinkTwiceProtocol=Full-data learning2026.03 | 62.44 | 31.23 | 27.38 | 18.42 | 35.82 | 50 | 54.23 | 37.17 | |
| UniADProtocol=Full-data learning2026.03 | 45.81 | 16.36 | 14.1 | 17.78 | 21.67 | 10 | 14.21 | 15.55 | |
| VADProtocol=Full-data learning2026.03 | 42.35 | 15 | 8.11 | 24.44 | 18.64 | 20 | 19.15 | 18.07 | |
| TCPProtocol=Full-data learning2026.03 | 40.7 | 15 | 16.18 | 20 | 20 | 10 | 6.69 | 14.63 | |
| AD-MLPProtocol=Full-data learning2026.03 | 18.05 | 0 | 0 | 0 | 0 | 0 | 4.35 | 0.87 |