Gemini 1.5
Google DeepMind — Gemini
partial detail 7 method fields published
Evaluation
AMC (American Mathematics Competitions)
American Mathematics Competitions problems; 1.5 Pro +13.2% over 1.0 Ultra; Flash +8.4%
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.