MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
- URL: http://arxiv.org/abs/2311.16502v4
- Date: Thu, 13 Jun 2024 15:02:39 GMT
- Title: MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
- Authors: Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen,
- Abstract summary: MMMU is a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks.
Questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types.
The evaluation of 14 open-source LMMs as well as the proprietary GPT-4V(ision) and Gemini highlights the substantial challenges posed by MMMU.
- Score: 64.21953221846596
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous 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 14 open-source LMMs as well as the proprietary 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
- MMSci: A Multimodal Multi-Discipline Dataset for PhD-Level Scientific Comprehension [59.41495657570397]
We collected a multimodal, multidisciplinary dataset from open-access scientific articles published in Nature Communications journals.
This dataset spans 72 scientific disciplines, ensuring both diversity and quality.
We created benchmarks with various tasks and settings to comprehensively evaluate LMMs' capabilities in understanding scientific figures and content.
arXiv Detail & Related papers (2024-07-06T00:40:53Z) - SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation [50.061029816288936]
We present SciFIBench, a scientific figure interpretation benchmark.
Our main benchmark consists of a 1000-question gold set of multiple-choice questions split between two tasks across 12 categories.
The questions are curated from CS arXiv paper figures and captions, using adversarial filtering to find hard negatives and human verification for quality control.
We evaluate 26 LMMs on SciFIBench, finding it to be a challenging benchmark.
arXiv Detail & Related papers (2024-05-14T17:54:17Z) - OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems [62.06169250463104]
We present OlympiadBench, an Olympiad-level bilingual multimodal scientific benchmark, featuring 8,476 problems from Olympiad-level mathematics and physics competitions.
The best-performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics.
Our analysis orienting GPT-4V points out prevalent issues with hallucinations, knowledge omissions, and logical fallacies.
arXiv Detail & Related papers (2024-02-21T18:49:26Z) - SceMQA: A Scientific College Entrance Level Multimodal Question
Answering Benchmark [42.91902601376494]
The paper introduces SceMQA, a novel benchmark for scientific multimodal question answering at the college entrance level.
SceMQA focuses on core science subjects including Mathematics, Physics, Chemistry, and Biology.
It features a blend of multiple-choice and free-response formats, ensuring a comprehensive evaluation of AI models' abilities.
arXiv Detail & Related papers (2024-02-06T19:16:55Z) - PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology [14.944207181507135]
We introduce PathMMU, the largest and highest-quality expert-validated pathology benchmark for Large Multimodal Models (LMMs)
It comprises 33,428 multimodal multi-choice questions and 24,067 images from various sources, each accompanied by an explanation for the correct answer.
The construction of PathMMU harnesses GPT-4V's advanced capabilities, utilizing over 30,000 image-caption pairs to enrich captions and generate corresponding Q&As.
arXiv Detail & Related papers (2024-01-29T17:59:19Z) - CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark [71.65760716397347]
We introduce a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context.
CMMMU includes 12k manually collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering.
CMMMU focuses on complex perception and reasoning with domain-specific knowledge in the Chinese context.
arXiv Detail & Related papers (2024-01-22T13:34:34Z) - Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge
Evaluation [61.56563631219381]
We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge.
Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 249,587 questions and accompanied by Xiezhi- Specialty and Xiezhi-Interdiscipline, both with 15k questions.
arXiv Detail & Related papers (2023-06-09T09:52:05Z) - M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark
for Chinese Large Language Models [35.17226595231825]
M3KE is a Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark.
It is developed to measure knowledge acquired by Chinese large language models.
We have collected 20,477 questions from 71 tasks.
arXiv Detail & Related papers (2023-05-17T14:56:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.