YiyangAiLab/MIRA

MIRA（多模态想象推理评估）是一个评估多模态语言模型在推理时是否能够边绘制边思考的数据集，即生成和使用中间视觉表征（草图、图表、轨迹）作为推理的一部分。MIRA包含546个精心挑选的问题，跨越20种任务类型，分布在四个领域：欧几里得几何、基于物理的推理、抽象空间与逻辑谜题、因果变换。每个实例都带有黄金视觉思维链图像和最终答案。

MIRA (Multimodal Imagination for Reasoning Assessment) is a benchmark to evaluate whether MLLMs can think while drawing—i.e., generate and use intermediate visual representations (sketches, diagrams, trajectories) as part of reasoning. MIRA includes 546 carefully curated problems spanning 20 task types across four domains: Euclidean Geometry (EG), Physics-Based Reasoning (PBR), Abstract Spatial & Logical Puzzles (ASLP), and Causal Transformations (CT). Each instance comes with gold visual chain-of-thought images and final answers.