Evaluation

Text-to-text helpfulness evaluation (SxS)

Side-by-side (SxS) quality metric comparing Gemini 1.5 Pro/Flash vs Gemini 1.0 Ultra on prompts where nuanced answers avoid policy violations; annotators also rate instruction following, refusals, quality, tone

Model behavior & alignment Google DeepMind — Gemini

Ask about this evaluation

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 Feb 2024

Google DeepMind — Gemini

rich detail 11 method fields published

See how this test was run