protologue

MMMU

MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark of college-level questions that require reasoning over images, such as charts, diagrams, tables, and chemical structures, together with text, across 30 subjects in six disciplines.

Description

It tests whether multimodal models can combine visual perception with domain knowledge, not only describe images. It is a standard headline score for vision-language models.

Sources

  1. Yue et al. (2023). MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI.

Cite this entry

Protologue. (2026). MMMU. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0196). https://protologue.com/t/mmmu/

BibTeX
@misc{protologue_mmmu,
  title = {MMMU},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.4.0},
  note = {Entry PTL-0196},
  url = {https://protologue.com/t/mmmu/}
}

Markdown JSON