While large multimodal models (LMMs) have demonstrated strong performance across various Visual Question Answering (VQA) tasks, certain challenges require complex multi-step reasoning to reach accurate answers. One particularly challenging task is autonomous driving, which demands thorough cognitive processing before decisions can be made. In this domain, a sequential and interpretive understanding of visual cues is essential for effective perception, prediction, and planning. Nevertheless, common VQA benchmarks often focus on the accuracy of the final answer while overlooking the reasoning process that enables the generation of accurate responses. Moreover, existing methods lack a comprehensive framework for evaluating step-by-step reasoning in realistic driving scenarios. To address this gap, we propose DriveLMM-o1, a new dataset and benchmark specifically designed to advance step-wise visual reasoning for autonomous driving. Our benchmark features over 18k VQA examples in the training set and more than 4k in the test set, covering diverse questions on perception, prediction, and planning, each enriched with step-by-step reasoning to ensure logical inference in autonomous driving scenarios. We further introduce a large multimodal model that is fine-tuned on our reasoning dataset, demonstrating robust performance in complex driving scenarios. In addition, we benchmark various open-source and closed-source methods on our proposed dataset, systematically comparing their reasoning capabilities for autonomous driving tasks. Our model achieves a +7.49% gain in final answer accuracy, along with a 3.62% improvement in reasoning score over the previous best open-source model. Our framework, dataset, and model are available atthis https URL.
View on arXiv@article{ishaq2025_2503.10621,
title={ DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding },
author={ Ayesha Ishaq and Jean Lahoud and Ketan More and Omkar Thawakar and Ritesh Thawkar and Dinura Dissanayake and Noor Ahsan and Yuhao Li and Fahad Shahbaz Khan and Hisham Cholakkal and Ivan Laptev and Rao Muhammad Anwer and Salman Khan },
journal={arXiv preprint arXiv:2503.10621},
year={ 2025 }
}