Benchmark

MMMU

Measures: 11.5K college-level multimodal questions across 30 subjects and 30 image types (charts, diagrams, music sheets, chemical structures); scored by accuracy on the validation or test set.

Maintainer
MMMU team (Xiang Yue et al.)
Introduced
2023
Status
Superseded
Saturation
Near-ceiling
Typical provenance
Mixed
In scoring set
No

PaperOfficial leaderboard

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.

MMMU: leaderboard and what it measures · supermarket.dev