# Closed-loop End-to-End Autonomous Driving on Bench2Drive (base set) Source: [Closed-loop End-to-End Autonomous Driving on Bench2Drive (base set)]() Collection index: [llms.txt]() Data updated: 2026-05-12T15:55:25.049Z Evaluation of Closed-loop End-to-End Autonomous Driving performance on the base set of the Bench2Drive dataset, reporting metrics including Driving Score (DS), Success Rate (SR), Efficiency, and Comfortness. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Closed-loop End-to-End Autonomous Driving | | Dataset (including any stated split) | Bench2Drive (base set) | | Metric | Driving Score (DS) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 17 of 17 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Driving Score (DS)](): Higher is better; unit: SCALAR. - [Success Rate (SR)](): Higher is better; unit: PERCENT. - [Efficiency](): Higher is better; unit: SCALAR. - [Comfortness](): Higher is better; unit: SCALAR. ## Recorded results | Method | Driving Score (DS) | Result date | Report paper | | --- | --- | --- | --- | | DeepSight | 86.23 | Not recorded | 6a02b481dbc836b87d824ca8 | | SimLingo | 85.94 | Not recorded | 6a02b481dbc836b87d824ca8 | | DeepSight w/o adaptive CoT | 84.52 | Not recorded | 6a02b481dbc836b87d824ca8 | | AutoVLA | 78.84 | Not recorded | 6a02b481dbc836b87d824ca8 | | ORION | 77.74 | Not recorded | 6a02b481dbc836b87d824ca8 | | DiffusionDrive | 77.68 | Not recorded | 6a02b481dbc836b87d824ca8 | | DriveAdapter\* | 64.22 | Not recorded | 6a02b481dbc836b87d824ca8 | | ReasonPlan | 64.01 | Not recorded | 6a02b481dbc836b87d824ca8 | | DriveTrans | 63.46 | Not recorded | 6a02b481dbc836b87d824ca8 | | ThinkTwice\* | 62.44 | Not recorded | 6a02b481dbc836b87d824ca8 | | TCP-traj\* | 59.9 | Not recorded | 6a02b481dbc836b87d824ca8 | | TCP-traj w/o distillation | 49.3 | Not recorded | 6a02b481dbc836b87d824ca8 | | GenAD | 44.81 | Not recorded | 6a02b481dbc836b87d824ca8 | | MomAD | 44.54 | Not recorded | 6a02b481dbc836b87d824ca8 | | VAD | 42.35 | Not recorded | 6a02b481dbc836b87d824ca8 | | TCP\* | 40.7 | Not recorded | 6a02b481dbc836b87d824ca8 | | TCP-ctrl\* | 30.47 | Not recorded | 6a02b481dbc836b87d824ca8 | ### DeepSight Driving Score (DS): 86.23. Result ID: 6a034d5c47f34ce924e89882. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paradigm":"VLM","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### SimLingo Driving Score (DS): 85.94. Result ID: 6a034d5c47f34ce924e89880. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paradigm":"VLM","Expert":"PDM-Lite"}. This record does not assert independent reproduction. ### DeepSight w/o adaptive CoT Driving Score (DS): 84.52. Result ID: 6a034d5c47f34ce924e89881. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paradigm":"VLM","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### AutoVLA Driving Score (DS): 78.84. Result ID: 6a034d5c47f34ce924e8987e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paradigm":"VLM","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### ORION Driving Score (DS): 77.74. Result ID: 6a034d5c47f34ce924e8987d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"VLM","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### DiffusionDrive Driving Score (DS): 77.68. Result ID: 6a034d5c47f34ce924e8987f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"PDM-Lite"}. This record does not assert independent reproduction. ### DriveAdapter\* Driving Score (DS): 64.22. Result ID: 6a034d5c47f34ce924e89877. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive","Expert feature distillation":"true"}. This record does not assert independent reproduction. ### ReasonPlan Driving Score (DS): 64.01. Result ID: 6a034d5c47f34ce924e8987c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"VLM","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### DriveTrans Driving Score (DS): 63.46. Result ID: 6a034d5c47f34ce924e8987b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### ThinkTwice\* Driving Score (DS): 62.44. Result ID: 6a034d5c47f34ce924e89876. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive","Expert feature distillation":"true"}. This record does not assert independent reproduction. ### TCP-traj\* Driving Score (DS): 59.9. Result ID: 6a034d5c47f34ce924e89874. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive","Expert feature distillation":"true"}. This record does not assert independent reproduction. ### TCP-traj w/o distillation Driving Score (DS): 49.3. Result ID: 6a034d5c47f34ce924e89875. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### GenAD Driving Score (DS): 44.81. Result ID: 6a034d5c47f34ce924e89879. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### MomAD Driving Score (DS): 44.54. Result ID: 6a034d5c47f34ce924e8987a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### VAD Driving Score (DS): 42.35. Result ID: 6a034d5c47f34ce924e89878. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive"}. This record does not assert independent reproduction. ### TCP\* Driving Score (DS): 40.7. Result ID: 6a034d5c47f34ce924e89872. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive","Expert feature distillation":"true"}. This record does not assert independent reproduction. ### TCP-ctrl\* Driving Score (DS): 30.47. Result ID: 6a034d5c47f34ce924e89873. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Expert":"Think2Drive","Expert feature distillation":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.