MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI

Citations Over TimeTop 1% of 2024 papers

Abstract

We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and text-books, covering six core disciplines: Art & Design, Busi-ness, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly het-erogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of 28 open-source LMMs as well as the propri-etary GPT-4V(ision) and Gemini highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V and Gemini Ultra only achieve accuracies of 56% and 59% respectively, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence.

Related Papers

• Theoretical Analysis of the Benchmark for Choosing Manipulative Instruments of Monetary Policies(2009)
• → Exploring disk performance benchmarks(2017)
• Susquehanna Chorale Spring Concert "Roots and Wings"(2017)
• → Support Structure Performance Benchmark(2023)
• → ИСПОЛЬЗОВAНИЕ ПОТЕНЦИAЛA СОЦИAЛЬНЫХ ПAРТНЕРОВ В ПОДГОТОВКЕ БУДУЩИХ ПЕДAГОГОВ(2024)