SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.04003 · ICCV · 2025

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 0 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 2 failures of our instrument; 0 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/2501.04003.json · badge: /api/ran/2501.04003.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
opendrivelab/drivelm canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_rotary_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
opendrivelab/drivelm/challenge/llama_adapter_v2_multimodal7b/llama/llama.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from meituan-automl/visionllama, is pointer only (licence: NONE) · get_code("b47d48e431b34acd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from meituan-automl/visionllama, and GitHub detected no licence in that repository 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.

precompute_freqs_cis Ran
ran, violated the contract we drafted
opendrivelab/drivelm/challenge/llama_adapter_v2_multimodal7b/llama/llama.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from meituan-automl/visionllama, is pointer only (licence: NONE) · get_code("14a84c2cbfebc413")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from meituan-automl/visionllama, and GitHub detected no licence in that repository 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.

reshape_for_broadcast Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
opendrivelab/drivelm/challenge/llama_adapter_v2_multimodal7b/llama/llama.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from alpha-vllm/llama2-accessory, is pointer only (licence: NOASSERTION) · get_code("70bf6ebaafd266c4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from alpha-vllm/llama2-accessory, and GitHub could not classify the licence of that repository (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.

rule_based1 Ran
ran on a synthesized input
opendrivelab/drivelm/challenge/convert_data.py
code served (permissive licence) · get_code("430efedcfc8bfbd4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import random

def rule_based1(question, answer):
    rule = ['Going ahead.', 'Turn right.', 'Turn left.', 'Stopped.', 'Back up.', 'Reverse parking.', 'Drive backward.']
    rule.remove(answer)
    choices = random.sample(rule, 3)
    choices.append(answer)
    random.shuffle(choices)
    idx = choices.index(answer)
    question += f' Please select the correct answer from the following options: A. {choices[0]} B. {choices[1]} C. {choices[2]} D. {choices[3]}'
    mapping = {0: 'A', 1: 'B', 2: 'C', 3: 'D'}
    return {'Q': question, 'A': mapping[idx]}

random.seed(42)

ARGS = {
    'question': 'What action should the vehicle take?',
    'answer': 'Turn right.'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rule_based2 Ran
ran on a synthesized input
opendrivelab/drivelm/challenge/convert_data.py
code served (permissive licence) · get_code("086ec56d0974ba63")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import random

def rule_based2(question, answer):
    rule = ['The ego vehicle is slightly steering to the left. The ego vehicle is driving very fast.', 'The ego vehicle is steering to the left. The ego vehicle is driving with normal speed.', 'The ego vehicle is steering to the left. The ego vehicle is driving fast.', 'The ego vehicle is slightly steering to the right. The ego vehicle is driving fast.', 'The ego vehicle is going straight. The ego vehicle is driving slowly.', 'The ego vehicle is going straight. The ego vehicle is driving with normal speed.', 'The ego vehicle is slightly steering to the left. The ego vehicle is driving with normal speed.', 'The ego vehicle is slightly steering to the left. The ego vehicle is driving slowly.', 'The ego vehicle is slightly steering to the right. The ego vehicle is driving slowly.', 'The ego vehicle is slightly steering to the right. The ego vehicle is driving very fast.', 'The ego vehicle is steering to the right. The ego vehicle is driving fast.', 'The ego vehicle is steering to the right. The ego vehicle is driving very fast.', 'The ego vehicle is slightly steering to the left. The ego vehicle is driving fast.', 'The ego vehicle is steering to the left. The ego vehicle is driving very fast.', 'The ego vehicle is going straight. The ego vehicle is not moving.', 'The ego vehicle is slightly steering to the right. The ego vehicle is driving with normal speed.', 'The ego vehicle is steering to the right. The ego vehicle is driving slowly.', 'The ego vehicle is steering to the right. The ego vehicle is driving with normal speed.', 'The ego vehicle is going straight. The ego vehicle is driving very fast.', 'The ego vehicle is going straight. The ego vehicle is driving fast.', 'The ego vehicle is steering to the left. The ego vehicle is driving slowly.']
    rule.remove(answer)
    choices = random.sample(rule, 3)
    choices.append(answer)
    random.shuffle(choices)
    idx = choices.index(answer)
    question += f' Please select the correct answer from the following options: A. {choices[0]} B. {choices[1]} C. {choices[2]} D. {choices[3]}'
    mapping = {0: 'A', 1: 'B', 2: 'C', 3: 'D'}
    return {'Q': question, 'A': mapping[idx]}

ARGS = {
    'question': 'What is the ego vehicle doing?',
    'answer': 'The ego vehicle is going straight. The ego vehicle is driving fast.'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 3 later) and 2 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
reshape_for_broadcast 58 other papers
49 dated earlier, 2 the same month, 6 later, 1 same year, order not determinable · 2 only as an assembly brick
2023.emnlp-main.534 (2023 (year only))
Disentangling Transformer Language Models as Superposed Topic Models
2303.09736 (2023-03)
Dynamic Structure Pruning for Compressing CNNs
2307.09288 (2023-07)
Llama 2: Open Foundation and Fine-Tuned Chat Models
and 55 more not named here
apply_rotary_emb 55 other papers
45 dated earlier, 1 the same month, 8 later, 1 same year, order not determinable · 1 only as an assembly brick
2023.emnlp-main.534 (2023 (year only))
Disentangling Transformer Language Models as Superposed Topic Models
2303.09736 (2023-03)
Dynamic Structure Pruning for Compressing CNNs
2307.09288 (2023-07)
Llama 2: Open Foundation and Fine-Tuned Chat Models
and 52 more not named here
precompute_freqs_cis 47 other papers
41 dated earlier, 5 later, 1 same year, order not determinable · 1 only as an assembly brick
2023.emnlp-main.534 (2023 (year only))
Disentangling Transformer Language Models as Superposed Topic Models
2303.09736 (2023-03)
Dynamic Structure Pruning for Compressing CNNs
2307.09288 (2023-07)
Llama 2: Open Foundation and Fine-Tuned Chat Models
and 44 more not named here

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

Figure 1. Overview of DriveBench. Our benchmark evaluates the reliability and visual grounding of Vision-Language Models (VLMs) in autonomous driving across four mainstream driving tasks -perception, prediction, planning, and behavior -under a diverse spectrum of 17 settings (clean, corrupted, and text-only inputs). It includes 19,200 frames and 20,498 QA pairs spanning three question types: multiple-choice, open-ended, and visual grounding. By addressing diverse tasks and conditions, we aim to reveal VLMs' limitations and promote reliable, interpretable autonomous driving.

For agents

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

get_harvested_code_for_paper("2501.04003")
get_code_for_paper("2501.04003")
have("2501.04003")

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

curl https://syntology.ai/api/ran/2501.04003.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.04003.svg)](https://syntology.ai/paper/2501.04003)

Connect an agent — have() is free.