Autonomous driving requires reliable perception and safe decision-making in complex scenarios. Recent vision-language models (VLMs) demonstrate reasoning and generalization abilities, opening new possibilities for autonomous driving; however, existing benchmarks often evaluate perception and decision-making separately, limit failure analysis with choice-only formats, or introduce evaluation bias through LLM-scored long-form outputs. To address these issues, we present Drive-P2D, a progressive perception-to-decision benchmark with 6,650 questions across Object, Scene, and Decision levels. Drive-P2D adopts a separated reasoning-and-answer protocol: final answers are scored objectively, while reasoning is analyzed to identify error modes exposed along the progressive perception-to-decision chain. We evaluate mainstream VLMs across all and high-risk scenarios, and further characterize the perception-to-decision capability boundary through correlation analysis and similar-scene robustness testing. Reasoning further exposes failure modes such as logical reasoning errors and semantic feature omissions, and we train a lightweight analyzer model to automate large-scale error-mode annotation of reasoning. Together, these designs provide practical insights for building safer and more reliable VLMs for real-world autonomous driving.
@article{arxiv.2601.14702,
title = {Drive-P2D: A Progressive Perception-to-Decision Benchmark for VLMs in Autonomous Driving},
author = {Zecong Tang and Zixu Wang and Yifei Wang and Weitong Lian and Tianjian Gao and Haoran Li and Tengju Ru and Lingyi Meng and Zhejun Cui and Yichen Zhu and Qi Kang and Kaixuan Wang and Yu Zhang},
journal= {arXiv preprint arXiv:2601.14702},
year = {2026}
}