Video foundation models generate visually realistic and temporally coherent content, but their reliability as world simulators depends on whether they capture physical, logical, and spatial constraints. Existing metrics such as Frechet Video Distance (FVD) emphasize perceptual quality and overlook reasoning failures, including violations of causality, physics, and global consistency. We introduce MMGR (Multi-Modal Generative Reasoning Evaluation and Benchmark), a principled evaluation framework based on five reasoning abilities: Physical, Logical, 3D Spatial, 2D Spatial, and Temporal. MMGR evaluates generative reasoning across three domains: Abstract Reasoning (ARC-AGI, Sudoku), Embodied Navigation (real-world 3D navigation and localization), and Physical Commonsense (sports and compositional interactions). MMGR applies fine-grained metrics that require holistic correctness across both video and image generation. We benchmark leading video models (Veo-3, Sora-2, Wan-2.2) and image models (Nano-banana, Nano-banana Pro, GPT-4o-image, Qwen-image), revealing strong performance gaps across domains. Models show moderate success on Physical Commonsense tasks but perform poorly on Abstract Reasoning (below 10 percent accuracy on ARC-AGI) and struggle with long-horizon spatial planning in embodied settings. Our analysis highlights key limitations in current models, including overreliance on perceptual data, weak global state consistency, and objectives that reward visual plausibility over causal correctness. MMGR offers a unified diagnostic benchmark and a path toward reasoning-aware generative world models.

翻译：视频基础模型能够生成视觉逼真且时序连贯的内容，但其作为世界模拟器的可靠性取决于其是否能够捕捉物理、逻辑与空间约束。现有评估指标（如弗雷歇视频距离FVD）侧重于感知质量，却忽视了推理层面的失效问题，包括对因果性、物理规律及全局一致性的违背。本文提出MMGR（多模态生成式推理评估与基准框架），这是一个基于五项推理能力构建的原则性评估框架：物理推理、逻辑推理、三维空间推理、二维空间推理与时序推理。MMGR在三个领域评估生成式推理能力：抽象推理（ARC-AGI、数独）、具身导航（真实世界三维导航与定位）以及物理常识（运动场景与组合交互）。MMGR采用细粒度评估指标，要求视频与图像生成在整体上均具备正确性。我们对主流视频模型（Veo-3、Sora-2、Wan-2.2）和图像模型（Nano-banana、Nano-banana Pro、GPT-4o-image、Qwen-image）进行了基准测试，揭示了各领域存在的显著性能差距。模型在物理常识任务上表现尚可，但在抽象推理领域表现不佳（ARC-AGI准确率低于10%），并在具身环境中的长时程空间规划任务上存在明显困难。我们的分析揭示了当前模型的关键局限，包括对感知数据的过度依赖、全局状态一致性薄弱，以及优化目标倾向于视觉合理性而非因果正确性。MMGR提供了一个统一的诊断性基准，并为构建具备推理意识的生成式世界模型指明了发展方向。