SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.03877 · NeurIPS · 2024

Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving

Junchi Yan, Zhiyuan Zhang, Xiaosong Jia, Zhenjie Yang, Qifeng Li

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 12 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.03877.json · badge: /api/ran/2406.03877.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
thinklab-sjtu/bench2drivezoo canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
Thinklab-SJTU/Bench2Drive canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
append_list_id Ran
ran; our contract draft was wrong, not the code
Thinklab-SJTU/Bench2Drive/B2DVisualize/visualizers/json_vis.py
pointer only (licence: NOASSERTION) · get_code("1eb24873f4386473")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Thinklab-SJTU/Bench2Drive (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

batched_nms Ran
ran; our contract draft was wrong, not the code
thinklab-sjtu/bench2drivezoo/mmcv/layers/nms.py
pointer only (licence: NOASSERTION) · get_code("d7527a665dfb8f27")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thinklab-sjtu/bench2drivezoo/mmcv/layers/wrappers.py
pointer only (licence: NOASSERTION) · get_code("2cc5addbe52bf811")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ciou_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thinklab-sjtu/bench2drivezoo/mmcv/layers/losses.py
pointer only (licence: NONE) · get_code("cee8870d4fbccc39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thinklab-sjtu/bench2drivezoo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

differentiable_all_reduce Ran
ran, honoured the contract we drafted
thinklab-sjtu/bench2drivezoo/mmcv/layers/batch_norm.py
pointer only (licence: NOASSERTION) · get_code("3b4490a3fe94a15c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

diou_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thinklab-sjtu/bench2drivezoo/mmcv/layers/losses.py
pointer only (licence: NONE) · get_code("26f3066ead0d2eec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thinklab-sjtu/bench2drivezoo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

empty_input_loss_func_wrapper Ran
ran; our contract draft was wrong, not the code
thinklab-sjtu/bench2drivezoo/mmcv/layers/wrappers.py
pointer only (licence: NOASSERTION) · get_code("0956a6506834357f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

filter_json_tree Ran
ran; our contract draft was wrong, not the code
Thinklab-SJTU/Bench2Drive/B2DVisualize/visualizers/json_vis.py
pointer only (licence: NOASSERTION) · get_code("96ccfa8cde1cf6ef")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Thinklab-SJTU/Bench2Drive (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_actor_display_name Ran
ran; our contract draft was wrong, not the code
Thinklab-SJTU/Bench2Drive/scenario_runner/manual_control.py
pointer only (licence: NONE); the stored copy get_code serves, from findaheng/Scenic, is pointer only (licence: NOASSERTION) · get_code("c882c504d11f2b36")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Thinklab-SJTU/Bench2Drive when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_masks Ran
ran; our contract draft was wrong, not the code
thinklab-sjtu/bench2drivezoo/mmcv/layers/mask_ops.py
pointer only (licence: NOASSERTION) · get_code("406f84cf799ed34d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

paste_mask_in_image_old Ran
ran; our contract draft was wrong, not the code
thinklab-sjtu/bench2drivezoo/mmcv/layers/mask_ops.py
pointer only (licence: NOASSERTION) · get_code("d03592674030077f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

paste_masks_in_image Ran
ran; our contract draft was wrong, not the code
thinklab-sjtu/bench2drivezoo/mmcv/layers/mask_ops.py
pointer only (licence: NOASSERTION) · get_code("c0eac7dcd1335fa1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

shapes_to_tensor Ran
ran; our contract draft was wrong, not the code
thinklab-sjtu/bench2drivezoo/mmcv/layers/wrappers.py
pointer only (licence: NOASSERTION) · get_code("d9acad9b929a7bb2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

batched_nms_rotated Not yet run
unverified (harvested, no recorded run)
thinklab-sjtu/bench2drivezoo/mmcv/layers/nms.py
pointer only (licence: NOASSERTION) · get_code("df39d2e76b0bb6d2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

cache_file Not yet run
unverified (harvested, no recorded run)
Thinklab-SJTU/Bench2Drive/B2DVisualize/util/cache.py
pointer only (licence: NOASSERTION) · get_code("3bcd1f43b044e1cd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Thinklab-SJTU/Bench2Drive (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

nms_rotated Not yet run
unverified (harvested, no recorded run)
thinklab-sjtu/bench2drivezoo/mmcv/layers/nms.py
pointer only (licence: NOASSERTION) · get_code("ecfd01cc7b6523f8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

pairwise_iou_rotated Not yet run
unverified (harvested, no recorded run)
thinklab-sjtu/bench2drivezoo/mmcv/layers/rotated_boxes.py
pointer only (licence: NOASSERTION) · get_code("df40c33628d29275")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, thinklab-sjtu/bench2drivezoo (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 12 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 1 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
pad_masks 22 other papers
22 dated earlier
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 19 more not named here
paste_mask_in_image_old 22 other papers
22 dated earlier
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 19 more not named here
get_actor_display_name 8 other papers
6 dated earlier, 2 later
1904.08980 (2019-04)
Exploring the Limitations of Behavior Cloning for Autonomous Driving
1911.04175 (2019-11)
Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning
1911.10868 (2019-11)
End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances
and 5 more not named here
cat 6 other papers
5 dated earlier, 1 same year, order not determinable
2004.08955 (2020-04)
ResNeSt: Split-Attention Networks
2203.15175 (2022-03)
Unified Transformer Tracker for Object Tracking
2301.02657 (2023-01)
TarViS: A Unified Approach for Target-based Video Segmentation
and 3 more not named here
ciou_loss 4 other papers
4 dated earlier
1708.02002 (2017-08)
Focal Loss for Dense Object Detection
2304.03752 (2023-04)
V3Det: Vast Vocabulary Visual Detection Dataset
2312.08875 (2023-12)
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?
and 1 more not named here
diou_loss 4 other papers
4 dated earlier
1708.02002 (2017-08)
Focal Loss for Dense Object Detection
2304.03752 (2023-04)
V3Det: Vast Vocabulary Visual Detection Dataset
2312.08875 (2023-12)
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?
and 1 more not named here
batched_nms 3 other papers
3 dated earlier
2304.03752 (2023-04)
V3Det: Vast Vocabulary Visual Detection Dataset
2312.08875 (2023-12)
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?
2403.10191 (2024-03)
Generative Region-Language Pretraining for Open-Ended Object Detection
paste_masks_in_image 3 other papers
3 dated earlier
2304.03752 (2023-04)
V3Det: Vast Vocabulary Visual Detection Dataset
2312.08875 (2023-12)
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?
2403.10191 (2024-03)
Generative Region-Language Pretraining for Open-Ended Object Detection
batched_nms_rotated 1 other paper
1 dated earlier
2312.08875 (2023-12)
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?
differentiable_all_reduce 1 other paper
1 same year, order not determinable
Wang_Zero-TPrune_Zero-Shot_Token_Pruning_through_Leveraging_of_the_Attention_Graph_CVPR_2024_paper (2024 (year only))
Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
nms_rotated 1 other paper
1 dated earlier
2312.08875 (2023-12)
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?
pairwise_iou_rotated 1 other paper
1 dated earlier
2312.08875 (2023-12)
What, How, and When Should Object Detectors Update in Continually Changing Test Domains?

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In an era marked by the rapid scaling of foundation models, autonomous driving technologies are approaching a transformative threshold where end-to-end autonomous driving (E2E-AD) emerges due to its potential of scaling up in the data-driven manner. However, existing E2E-AD methods are mostly evaluated under the open-loop log-replay manner with L2 errors and collision rate as metrics (e.g., in nuScenes), which could not fully reflect the driving performance of algorithms as recently acknowledged in the community. For those E2E-AD methods evaluated under the closed-loop protocol, they are tested in fixed routes (e.g., Town05Long and Longest6 in CARLA) with the driving score as metrics, which is known for high variance due to the unsmoothed metric function and large randomness in the long route. Besides, these methods usually collect their own data for training, which makes algorithm-level fair comparison infeasible. To fulfill the paramount need of comprehensive, realistic, and fair testing environments for Full Self-Driving (FSD), we present Bench2Drive, the first benchmark for evaluating E2E-AD systems' multiple abilities in a closed-loop manner. Bench2Drive's official training data consists of 2 million fully annotated frames, collected from 13638 short clips uniformly distributed under 44 interactive scenarios (cut-in, overtaking, detour, etc), 23 weathers (sunny, foggy, rainy, etc), and 12 towns (urban, village, university, etc) in CARLA v2. Its evaluation protocol requires E2E-AD models to pass 44 interactive scenarios under different locations and weathers which sums up to 220 routes and thus provides a comprehensive and disentangled assessment about their driving capability under different situations. We implement state-of-the-art E2E-AD models and evaluate them in Bench2Drive, providing insights regarding current status and future directions.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.03877")
get_code_for_paper("2406.03877")
have("2406.03877")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.03877.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.03877.svg)](https://syntology.ai/paper/2406.03877)

Connect an agent — have() is free.