Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
Sichuan University · Shanghai Jiao Tong University · Zhejiang University · University of the Chinese Academy of Sciences · Tongji University · Shanghai Artificial Intelligence Laboratory · Fudan University · East China Normal University · Georgia Institute of Technology · The Chinese University of Hong Kong · Chinese University of Hong Kong · Nanjing University of Information Science and Technology · Machine Intelligence Laboratory College of Computer Science, Sichuan University · UNSW, Sydney
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Scientific discoveries increasingly rely on complex multimodal reasoning based on information-intensive scientific data and domain-specific expertise. Empowered by expert-level scientific benchmarks, scientific Multimodal Large Language Models (MLLMs) hold the potential to significantly enhance this discovery process in realistic workflows. However, current scientific benchmarks mostly focus on evaluating the knowledge understanding capabilities of MLLMs, leading to an inadequate assessment of their perception and reasoning abilities. To address this gap, we present the Scientists’ First Exam (SFE) benchmark, designed to evaluate the scientific cognitive capacities of MLLMs through three interconnected levels: *scientific signal perception*, *scientific attribute understanding*, *scientific comparative reasoning*. Specifically, SFE comprises 830 expert-verified VQA pairs across three question types, spanning 66 multimodal tasks across five high-value disciplines. Extensive experiments reveal that current *state-of-the-art* GPT-o3 and InternVL-3 achieve only 34.08% and 26.52% on SFE, highlighting significant room for MLLMs to improve in scientific realms. We hope the insights obtained in SFE will facilitate further developments in AI-enhanced scientific discoveries.