MMVU: Measuring Expert-Level Multi-Discipline Video Understanding

TL;DR

MMVU is a new comprehensive benchmark for evaluating foundation models in expert-level, multi-discipline video understanding, emphasizing domain-specific reasoning and high-quality annotations.

Contribution

It introduces a large, expert-annotated dataset with domain knowledge and reasoning, advancing evaluation of models in specialized video understanding tasks.

Findings

State-of-the-art models still lag behind human experts.

Models perform better with domain-specific reasoning.

Error analysis reveals key challenges for future research.

Abstract

We introduce MMVU, a comprehensive expert-level, multi-discipline benchmark for evaluating foundation models in video understanding. MMVU includes 3,000 expert-annotated questions spanning 27 subjects across four core disciplines: Science, Healthcare, Humanities & Social Sciences, and Engineering. Compared to prior benchmarks, MMVU features three key advancements. First, it challenges models to apply domain-specific knowledge and perform expert-level reasoning to analyze specialized-domain videos, moving beyond the basic visual perception typically assessed in current video benchmarks. Second, each example is annotated by human experts from scratch. We implement strict data quality controls to ensure the high quality of the dataset. Finally, each example is enriched with expert-annotated reasoning rationals and relevant domain knowledge, facilitating in-depth analysis. We conduct an extensive evaluation of 32 frontier multimodal foundation models on MMVU. The latest System-2-capable models, o1 and Gemini 2.0 Flash Thinking, achieve the highest performance among the tested models. However, they still fall short of matching human expertise. Through in-depth error analyses and case studies, we offer actionable insights for future advancements in expert-level, knowledge-intensive video understanding for specialized domains.