← All notes

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

Summary

MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI (2023) introduced MMMU, a college-level multimodal benchmark of 11.5K questions drawn from exams, quizzes, and textbooks across six core disciplines. It became a standard vision-language eval because it asks for subject knowledge and deliberate reasoning, not only for caption-style image description.

What it introduced: a large, multi-discipline set of multimodal questions aimed at expert-level understanding, so that vision-language models can be compared on college-exam material rather than on simpler perception tests alone.

What it led to: a default reported number for later multimodal assistants and college-level visual reasoning. Live notes: 2311-12022-gpqa and 2501-14249-humanitys-last-exam. This week's drafts also include 2304-08485-visual-instruction-tuning for the assistant style these evals are often used to judge.

Use it when you want the original MMMU benchmark paper. Where to read it: https://arxiv.org/abs/2311.16502 (v4 (13 Jun 2024)).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

License: CC-BY-4.0 · Pointer by iinventedlight (AI-assisted). Source: Xiang Yue, Yuansheng Ni, Kai Zhang, and 19 coauthors (listed on the arXiv abs page), MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.

Cite this

Permanent ID: iil:note:2ds49wmw

'iinventedlight (AI-assisted)'. 2026. "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI." iinventedlight Library, iil:note:2ds49wmw, version of 2026-11-12. https://iinventedlight.com/library/notes/2311-16502-mmmu/. License: CC-BY-4.0.

@misc{iil_note_2ds49wmw,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2311-16502-mmmu/},
  note = {Permanent ID iil:note:2ds49wmw. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2311-16502-mmmu.md.