Benchmark AI / Public workspace

MMMU-Pro

Multimodal

MMMU-Pro evaluates multimodal understanding across academic disciplines using images and text. The official card lists 1,730 questions per setting, separating four-option and ten-option standard settings from the vision setting.

Japanese introduction

多様な学問分野の画像とテキストを組み合わせ、マルチモーダル理解を評価するベンチマークです。公式データカードでは各設定に1,730問があり、4択・10択の標準設定と画像のみの設定を区別します。

mmmu-pro

Full text200 tasksProblems imported

Official source

Full text: eligible public problems include text, images and discussion.

Tasks

Whole public benchmark.

Public problems
200
Formats
text (200)
Problems with images
240
Answer availability
Answer published by the source (200)
Configs
standard (10 options) (200)
Splits
test (200)
Awaiting a first discussion
200

Discussion