Skip to content

Evaluation

MMMU (Massive Multi-discipline Multimodal Understanding)

Questions about images across 6 disciplines with multiple subjects requiring college-level knowledge

Multimodal Google DeepMind — Gemini

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Gemini 1.0
Google DeepMind — Gemini

rich detail 11 method fields published

See how this test was run