VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
University of Science and Technology of China · Xi'an Jiaotong University · Fudan University · Nanjing University · South China University of Technology, Tsinghua University · Shanghai AI Laboratory · Tsinghua University, Tsinghua University · Shanghai Artificial Intelligence Laboratory
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow language-based reasoning shortcuts, failing to measure genuine vision-centric reasoning. To address this, we introduce VisuLogic: a benchmark of 1,000 human-verified problems across six categories (e.g., quantitative shifts, spatial relations, attribute comparisons). These various types of questions can be evaluated to assess the visual reasoning capabilities of MLLMs from multiple perspectives. We evaluate leading MLLMs on this benchmark and analyze their results to identify common failure modes. Most models score below 30\% accuracy—only slightly above the 25\% random baseline and far below the 51.4\% achieved by humans—revealing significant gaps in visual reasoning.