Skip to content

Evaluation

MMLU (Gemini 1.5)

MMLU benchmark; 57 subjects; 1.0 Ultra, 1.5 Pro, 1.5 Flash all exceed 80%

Core capabilities 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 1.5
Google DeepMind — Gemini

partial detail 8 method fields published

See how this test was run