Gemini 1.0
Google DeepMind — Gemini
rich detail 12 method fields published
Evaluation
WMT 23 (machine translation benchmark)
WMT 23 translation benchmark across the entire set of language pairs in few-shot setting; out-of-English translation quality
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.