---
title: 'MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2311-16502-mmmu.md
source_license: 'arXiv non-exclusive distribution license'
attribution: '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.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: evals'
tags: arxiv, evals, multimodal, benchmarks
arxiv_id: 2311.16502
alias: 2311.16502-mmmu
type: pointer
format: pointer
sources:
  - id: S1
    title: 'MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI'
    publisher: arXiv
    authors: 'Xiang Yue, Yuansheng Ni, Kai Zhang, and 19 coauthors (listed on the arXiv abs page)'
    url: https://arxiv.org/abs/2311.16502
    version_read: 'v4 (13 Jun 2024)'
    accessed: 2026-11-12
    license: 'arXiv non-exclusive distribution license'
---
# 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](https://arxiv.org/abs/2311.16502) (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](https://iinventedlight.com/library/notes/2311-12022-gpqa/) and [2501-14249-humanitys-last-exam](https://iinventedlight.com/library/notes/2501-14249-humanitys-last-exam/). This week's drafts also include [2304-08485-visual-instruction-tuning](https://iinventedlight.com/library/notes/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.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).
