Gemma 2
Google DeepMind — Gemma
partial detail 18 method fields published
Evaluation
Evaluating the 2B and 9B models
distilled 2B and 9B models compared with previous Gemma 1 versions and standard open models across a variety of benchmarks; average performance on the 8 benchmarks comparable with LLaMA-3 and on all benchmarks
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.