MMMU-Pro

Vision

Massive Multi-discipline Multimodal Understanding (harder version).

Metrics
Accuracy (%)
Paper Dataset Eval Code

How to Run

pip install lmms-eval && lmms-eval --model MODEL --tasks mmmu_pro

Leaderboard

Rank Model Provider Parameters Score
1 GPT-5.2 OpenAI Unknown 86.5%
2 Gemini 3 Pro Google Unknown 81.0%