# Autonomous Driving on Bench2Drive 220 short segment scenarios Source: [Autonomous Driving on Bench2Drive 220 short segment scenarios]() Collection index: [llms.txt]() Data updated: 2026-03-09T08:50:59.445Z Evaluation of Autonomous Driving performance specifically on the '220 short segment scenarios' subset of the Bench2Drive dataset, reporting key metrics like Driving Score and Success Rate. 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) | Bench2Drive 220 short segment scenarios | | Metric | Driving Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 30 of 30 | | 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](): Higher is better; unit: SCALAR. - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Driving Score | Result date | Report paper | | --- | --- | --- | --- | | Expert | 82.37 | Not recorded | 68fa74e41e209131cea64777 | | Expert | 82.37 | Not recorded | 68fa77381e209131cea71c11 | | VL (on failure) | 77.3 | Not recorded | 68fa74e41e209131cea64777 | | Expert | 75.82 | Not recorded | 68fa74e41e209131cea64777 | | Expert | 75.82 | Not recorded | 68fa77381e209131cea71c11 | | IL + RL | 74.57 | Not recorded | 68fa74e41e209131cea64777 | | VL (on failure) | 73.29 | Not recorded | 68fa74e41e209131cea64777 | | CAPS | 68.91 | Not recorded | 68fa77381e209131cea71c11 | | CAPS | 66.76 | Not recorded | 68fa77381e209131cea71c11 | | DriveAdapter | 64.22 | Not recorded | 68fa74e41e209131cea64777 | | DriveAdapter | 64.22 | Not recorded | 68fa77381e209131cea71c11 | | ThinkTwice | 62.44 | Not recorded | 68fa74e41e209131cea64777 | | ThinkTwice | 62.44 | Not recorded | 68fa77381e209131cea71c11 | | IL with Uniform Sampling | 62.26 | Not recorded | 68fa77381e209131cea71c11 | | WoTE | 61.71 | Not recorded | 68fa77dd1e209131cea75ab0 | | VL (on expert) | 60.01 | Not recorded | 68fa74e41e209131cea64777 | | IL | 59.96 | Not recorded | 68fa74e41e209131cea64777 | | TCP-traj | 59.9 | Not recorded | 68fa74e41e209131cea64777 | | TCP | 59.9 | Not recorded | 68fa77dd1e209131cea75ab0 | | TCP-traj | 59.9 | Not recorded | 68fa77381e209131cea71c11 | | IL with Uniform Sampling | 59.49 | Not recorded | 68fa77381e209131cea71c11 | | UniAD-Base | 45.81 | Not recorded | 68fa74e41e209131cea64777 | | UniAD | 45.81 | Not recorded | 68fa77dd1e209131cea75ab0 | | UniAD-Base | 45.81 | Not recorded | 68fa77381e209131cea71c11 | | VAD | 42.35 | Not recorded | 68fa74e41e209131cea64777 | | VAD | 42.35 | Not recorded | 68fa77dd1e209131cea75ab0 | | VAD | 42.35 | Not recorded | 68fa77381e209131cea71c11 | | AD-MLP | 18.05 | Not recorded | 68fa74e41e209131cea64777 | | AD-MLP | 18.05 | Not recorded | 68fa77dd1e209131cea75ab0 | | AD-MLP | 18.05 | Not recorded | 68fa77381e209131cea71c11 | ### Expert Driving Score: 82.37. Result ID: 699369e13a6c31484915c478. [Reporting paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### Expert Driving Score: 82.37. Result ID: 69ae89dc6dbb7075b956c9f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### VL (on failure) Driving Score: 77.3. Result ID: 699369e13a6c31484915c477. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### Expert Driving Score: 75.82. Result ID: 699369e13a6c31484915c480. [Reporting paper]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### Expert Driving Score: 75.82. Result ID: 69ae89dc6dbb7075b956c9fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### IL + RL Driving Score: 74.57. Result ID: 699369e13a6c31484915c476. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### VL (on failure) Driving Score: 73.29. Result ID: 699369e13a6c31484915c47f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### CAPS Driving Score: 68.91. Result ID: 69ae89dc6dbb7075b956c9f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### CAPS Driving Score: 66.76. Result ID: 69ae89dc6dbb7075b956c9f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### DriveAdapter Driving Score: 64.22. Result ID: 699369e13a6c31484915c47e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### DriveAdapter Driving Score: 64.22. Result ID: 69ae89dc6dbb7075b956c9f7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### ThinkTwice Driving Score: 62.44. Result ID: 699369e13a6c31484915c47d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### ThinkTwice Driving Score: 62.44. Result ID: 69ae89dc6dbb7075b956c9f6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### IL with Uniform Sampling Driving Score: 62.26. Result ID: 69ae89dc6dbb7075b956c9ef. [Reporting paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### WoTE Driving Score: 61.71. Result ID: 69956dbf3badfaffe6627075. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Traj. Eval.":"Model-based"}. This record does not assert independent reproduction. ### VL (on expert) Driving Score: 60.01. Result ID: 699369e13a6c31484915c475. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### IL Driving Score: 59.96. Result ID: 699369e13a6c31484915c474. [Reporting paper]() Recorded evaluation configuration: {"Input":"Privileged"}. This record does not assert independent reproduction. ### TCP-traj Driving Score: 59.9. Result ID: 699369e13a6c31484915c47c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### TCP Driving Score: 59.9. Result ID: 69956dbf3badfaffe6627074. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TCP-traj Driving Score: 59.9. Result ID: 69ae89dc6dbb7075b956c9f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### IL with Uniform Sampling Driving Score: 59.49. Result ID: 69ae89dc6dbb7075b956c9f8. [Reporting paper]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### UniAD-Base Driving Score: 45.81. Result ID: 699369e13a6c31484915c47a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### UniAD Driving Score: 45.81. Result ID: 69956dbf3badfaffe6627072. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Traj. Eval.":"Rule-based"}. This record does not assert independent reproduction. ### UniAD-Base Driving Score: 45.81. Result ID: 69ae89dc6dbb7075b956c9f3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### VAD Driving Score: 42.35. Result ID: 699369e13a6c31484915c47b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### VAD Driving Score: 42.35. Result ID: 69956dbf3badfaffe6627073. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Traj. Eval.":"Rule-based"}. This record does not assert independent reproduction. ### VAD Driving Score: 42.35. Result ID: 69ae89dc6dbb7075b956c9f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. ### AD-MLP Driving Score: 18.05. Result ID: 699369e13a6c31484915c479. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Camera"}. This record does not assert independent reproduction. ### AD-MLP Driving Score: 18.05. Result ID: 69956dbf3badfaffe6627071. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AD-MLP Driving Score: 18.05. Result ID: 69ae89dc6dbb7075b956c9f2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Sensor"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.