Model Library / Benchmarks / MMMU

Multimodal

MMMU

Massive Multi-discipline Multimodal Understanding — college-level questions that require reasoning over images, charts, and diagrams.

Features measured

Vision Reasoning

Use cases unlocked

Document & image understanding Chart & diagram analysis Visual Q&A

Leaderboard

Higher is better · accuracy %

Bars scaled from 60 so close scores stay legible — the figure at right is the actual accuracy %.

Benchmark source ↗

← All benchmarks