ModelRefs / MMMU-Pro Leaderboard — AI Model Scores

MMMU-Pro Leaderboard — AI Model Scores

Harder, contamination-resistant successor to MMMU. Current leaders, methodology, and citation sources for MMMU-Pro.

Overview

Harder, contamination-resistant successor to MMMU.

How it is measured: Vision-only and standard splits; reported as mean.

How this benchmark is scored

Categorymultimodal
Maximum score100 % accuracy
DirectionHigher is better

Primary source: https://mmmu-benchmark.github.io/

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to MMMU-Pro Leaderboard — AI Model Scores.