Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.14145 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915863294115840 |
|---|---|
| author | Goel, Arushi Ghosh, Sreyan Agarwal, Vatsal Anand, Nishit Jayakumar, Kaousheik Koroshinadze, Lasha Xu, Yao Lyons, Katie Case, James Sapra, Karan Shih, Kevin J. Gururani, Siddharth Shrivastava, Abhinav Duraiswami, Ramani Manocha, Dinesh Tao, Andrew Catanzaro, Bryan Shoeybi, Mohammad Ping, Wei |
| author_facet | Goel, Arushi Ghosh, Sreyan Agarwal, Vatsal Anand, Nishit Jayakumar, Kaousheik Koroshinadze, Lasha Xu, Yao Lyons, Katie Case, James Sapra, Karan Shih, Kevin J. Gururani, Siddharth Shrivastava, Abhinav Duraiswami, Ramani Manocha, Dinesh Tao, Andrew Catanzaro, Bryan Shoeybi, Mohammad Ping, Wei |
| contents | Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and complex videos remains largely unexplored. We introduce MMOU, a new benchmark designed to systematically evaluate multimodal understanding and reasoning under these challenging, real-world conditions. MMOU consists of 15,000 carefully curated questions paired with 9038 web-collected videos of varying length, spanning diverse domains and exhibiting rich, tightly coupled audio-visual content. The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time. All questions are manually annotated across multiple turns by professional annotators, ensuring high quality and reasoning fidelity. We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU. The results expose substantial performance gaps: the best closed-source model achieves only 64.2% accuracy, while the strongest open-source model reaches just 46.8%. Our results highlight the challenges of long-form omni-modal understanding, revealing that current models frequently fail to apply even fundamental skills in long videos. Through detailed analysis, we further identify systematic failure modes and provide insights into where and why current models break. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14145 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos Goel, Arushi Ghosh, Sreyan Agarwal, Vatsal Anand, Nishit Jayakumar, Kaousheik Koroshinadze, Lasha Xu, Yao Lyons, Katie Case, James Sapra, Karan Shih, Kevin J. Gururani, Siddharth Shrivastava, Abhinav Duraiswami, Ramani Manocha, Dinesh Tao, Andrew Catanzaro, Bryan Shoeybi, Mohammad Ping, Wei Computation and Language Computer Vision and Pattern Recognition Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and complex videos remains largely unexplored. We introduce MMOU, a new benchmark designed to systematically evaluate multimodal understanding and reasoning under these challenging, real-world conditions. MMOU consists of 15,000 carefully curated questions paired with 9038 web-collected videos of varying length, spanning diverse domains and exhibiting rich, tightly coupled audio-visual content. The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time. All questions are manually annotated across multiple turns by professional annotators, ensuring high quality and reasoning fidelity. We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU. The results expose substantial performance gaps: the best closed-source model achieves only 64.2% accuracy, while the strongest open-source model reaches just 46.8%. Our results highlight the challenges of long-form omni-modal understanding, revealing that current models frequently fail to apply even fundamental skills in long videos. Through detailed analysis, we further identify systematic failure modes and provide insights into where and why current models break. |
| title | MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.14145 |