Gemini 1.5
Google DeepMind — Gemini
partial detail 7 method fields published
Evaluation
Hendrycks MATH benchmark; 1.5 Pro +14.5% over 1.0 Ultra; Flash +22.3% over 1.0 Pro
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.
partial detail 7 method fields published