# Autonomous Driving on CARLA Bench2Drive Leaderboard (test) Source: [Autonomous Driving on CARLA Bench2Drive Leaderboard (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:56.221Z Evaluation of general Autonomous Driving performance on the CARLA Bench2Drive Leaderboard test set, reporting granular metrics covering efficiency, comfort, success rate, and performance on specific maneuvers (Merging, Overtaking, Give Way, Traffic Sign compliance). 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 | Autonomous Driving | | Dataset (including any stated split) | CARLA Bench2Drive Leaderboard (test) | | Metric | Efficiency Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Efficiency Score](): Higher is better; unit: PERCENT. - [Comfort Score](): Higher is better; unit: PERCENT. - [Success Rate](): Higher is better; unit: PERCENT. - [DS Score](): Higher is better; unit: SCALAR. - [Merging Success Rate](): Higher is better; unit: PERCENT. - [Overtaking Success Rate](): Higher is better; unit: PERCENT. - [Emergency Braking Score](): Higher is better; unit: PERCENT. - [Give Way Compliance Rate](): Higher is better; unit: PERCENT. - [Traffic Sign Compliance Rate](): Higher is better; unit: PERCENT. - [Mean Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Efficiency Score | Result date | Report paper | | --- | --- | --- | --- | | VAD | 1.5794 | Not recorded | 68fa7ba21e209131cea89839 | | ReCogDrive | 1.3818 | Not recorded | 68fa7ba21e209131cea89839 | | UniAD-B. | 1.2921 | Not recorded | 68fa7ba21e209131cea89839 | | UniAD-T. | 1.2392 | Not recorded | 68fa7ba21e209131cea89839 | | Drive Transformer-L. | 1.0064 | Not recorded | 68fa7ba21e209131cea89839 | | TCP-traj | 0.7878 | Not recorded | 68fa7ba21e209131cea89839 | | ThinkTwice | 0.7693 | Not recorded | 68fa7ba21e209131cea89839 | | TCP-traj | 0.7654 | Not recorded | 68fa7ba21e209131cea89839 | | DriveAdapter | 0.7022 | Not recorded | 68fa7ba21e209131cea89839 | | TCP-ctrl | 0.5597 | Not recorded | 68fa7ba21e209131cea89839 | | TCP | 0.5426 | Not recorded | 68fa7ba21e209131cea89839 | | AD-MLP | 0.4845 | Not recorded | 68fa7ba21e209131cea89839 | ### VAD Efficiency Score: 1.5794. Result ID: 698b88f77a967eddb76f624c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ReCogDrive Efficiency Score: 1.3818. Result ID: 698b88f77a967eddb76f624e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UniAD-B. Efficiency Score: 1.2921. Result ID: 698b88f77a967eddb76f624b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"Base"}. This record does not assert independent reproduction. ### UniAD-T. Efficiency Score: 1.2392. Result ID: 698b88f77a967eddb76f624a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"Tiny"}. This record does not assert independent reproduction. ### Drive Transformer-L. Efficiency Score: 1.0064. Result ID: 698b88f77a967eddb76f624d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"Large"}. This record does not assert independent reproduction. ### TCP-traj Efficiency Score: 0.7878. Result ID: 698b88f77a967eddb76f6246. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distillation":"No"}. This record does not assert independent reproduction. ### ThinkTwice Efficiency Score: 0.7693. Result ID: 698b88f77a967eddb76f6247. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TCP-traj Efficiency Score: 0.7654. Result ID: 698b88f77a967eddb76f6245. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distillation":"Yes"}. This record does not assert independent reproduction. ### DriveAdapter Efficiency Score: 0.7022. Result ID: 698b88f77a967eddb76f6248. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TCP-ctrl Efficiency Score: 0.5597. Result ID: 698b88f77a967eddb76f6244. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Control":"Standard"}. This record does not assert independent reproduction. ### TCP Efficiency Score: 0.5426. Result ID: 698b88f77a967eddb76f6243. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"Default"}. This record does not assert independent reproduction. ### AD-MLP Efficiency Score: 0.4845. Result ID: 698b88f77a967eddb76f6249. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.