Gemini 1.5
Google DeepMind — Gemini
rich detail 9 method fields published
Evaluation
Hard externally proposed real-world GenAI use cases (preference evaluation)
Novel methodology using hundreds of real-world challenging, long-tail, complex prompts shared on the Internet and social media; relative human rater preference (win/tie/loss) vs Gemini 1.0 Pro and Ultra
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.