Metadata
| Source Table | benchmarks |
| Source ID | JqiV5SDIh9 |
| Description | Massive Multi-discipline Multimodal Understanding — 11,500 questions from college exams across 30 subjects and 6 disciplines, requiring college-level reasoning over images. |
| Wiki ID | mmmu |
| Children | — |
| Created | Mar 24, 2026, 11:23 PM |
| Updated | Mar 24, 2026, 11:24 PM |
| Synced | Mar 24, 2026, 11:24 PM |
Record Data
id | JqiV5SDIh9 |
slug | mmmu |
name | MMMU |
category | multimodal |
subCategory | — |
description | Massive Multi-discipline Multimodal Understanding — 11,500 questions from college exams across 30 subjects and 6 disciplines, requiring college-level reasoning over images. |
website | — |
scoringMethod | accuracy |
higherIsBetter | Yes |
introducedDate | 2023-11 |
maintainer | — |
source | arxiv.org/abs/2311.16502 |
Debug info
Thing ID: JqiV5SDIh9
Source Table: benchmarks
Source ID: JqiV5SDIh9
Wiki ID: mmmu