Gemini 1.0
Google DeepMind — Gemini
rich detail 10 method fields published
Evaluation
Internal benchmark measuring human preference for models with tool access (Gemini Extensions: Google Workspace, Maps, YouTube, Flights, Hotels) vs without, in domains like travel planning and video discovery
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.
rich detail 10 method fields published