Skip to content
Inside the Frontier

Evaluation

Using Gemma 2 instead of Gemma 1

PaliGemma 2 vs PaliGemma transfer scores at the same resolution and model size (3B), averaged over the 30+ academic benchmarks

Multimodal Google DeepMind — Gemma
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.

PaliGemma 2
Google DeepMind — Gemma

partial detail 18 method fields published

See how this test was run