Video generative models show emerging reasoning behaviors. It is essential to ensure that generated events remain causally consistent across frames for reliable deployment, a property we define as reasoning coherence. To bridge the gap in literature for missing reasoning coherence evaluation, we propose MME-CoF-Pro, a comprehensive video reasoning benchmark to assess reasoning coherence in video models. Specifically, MME-CoF-Pro contains 303 samples across 16 categories, ranging from visual logical to scientific reasoning. It introduces Reasoning Score as evaluation metric for assessing process-level necessary intermediate reasoning steps, and includes three evaluation settings, (a) no hint (b) text hint and (c) visual hint, enabling a controlled investigation into the underlying mechanisms of reasoning hint guidance. Evaluation results in 7 open and closed-source video models reveals insights including: (1) Video generative models exhibit weak reasoning coherence, decoupled from generation quality. (2) Text hints boost apparent correctness but often cause inconsistency and hallucinated reasoning (3) Visual hints benefit structured perceptual tasks but struggle with fine-grained perception. Website: https://video-reasoning-coherence.github.io/

翻译：视频生成模型展现出新兴的推理行为。为确保模型能可靠部署，必须保证生成事件在时间帧间保持因果一致性，我们将这一特性定义为推理连贯性。为填补文献中推理连贯性评估的空白，我们提出MME-CoF-Pro——一个用于评估视频模型推理连贯性的综合性视频推理基准。具体而言，MME-CoF-Pro包含覆盖16个类别（从视觉逻辑到科学推理）的303个样本。该基准引入推理得分作为评估指标，用于评估过程级必要中间推理步骤，并包含三种评估设置：(a) 无提示、(b) 文本提示和(c) 视觉提示，从而实现对推理提示引导机制的受控研究。在7个开源与闭源视频模型上的评估结果揭示了以下发现：(1) 视频生成模型推理连贯性薄弱，且与生成质量解耦；(2) 文本提示能提升表面正确性，但常导致不一致性和幻觉推理；(3) 视觉提示有助于结构化感知任务，但在细粒度感知方面表现欠佳。网站：https://video-reasoning-coherence.github.io/