// BENCHMARK

MMMU-Pro (Standard) benchmark

AI model leaderboard for the MMMU-Pro (Standard) benchmark. Compare how large language models score on MMMU-Pro (Standard), see the full ranking, and understand what this AI benchmark measures. Magistral Medium 1.1 currently leads with 57.9. Standard split of MMMU-Pro — 10-option multiple-choice text+image questions across college-level disciplines.

Leaderboard

# Model Organization Score Variant Source
#1 Magistral Medium 1.1 Mistral AI 57.9 official ↗
#2 Mistral Medium 3 Mistral AI 53.5 cited-magistral official ↗
#3 Magistral Small 1.1 Mistral AI 51.8 official ↗
#4 Mistral Small 3.1 Mistral AI 45.8 cited-magistral official ↗

Frequently asked questions about MMMU-Pro (Standard)

What is the MMMU-Pro (Standard) benchmark?

Standard split of MMMU-Pro — 10-option multiple-choice text+image questions across college-level disciplines.

How is the MMMU-Pro (Standard) benchmark scored?

MMMU-Pro (Standard) is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on MMMU-Pro (Standard)?

As of the latest reported scores on GenAIList, Magistral Medium 1.1 achieves the highest result on MMMU-Pro (Standard) with a score of 57.9.

Is a higher MMMU-Pro (Standard) score better?

Yes. On MMMU-Pro (Standard) a higher score indicates better performance, so models near the top of the leaderboard are the strongest.