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/
@article{arxiv.2603.20194,
title = {MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints},
author = {Yu Qi and Xinyi Xu and Ziyu Guo and Siyuan Ma and Renrui Zhang and Xinyan Chen and Ruichuan An and Ruofan Xing and Jiayi Zhang and Haojie Huang and Pheng-Ann Heng and Jonathan Tremblay and Lawson L. S. Wong},
journal= {arXiv preprint arXiv:2603.20194},
year = {2026}
}