Skip to content

Evaluation

Multimodal transfer evaluation vs PaliGemma 2

fine-tuning of multimodal Gemma 3 pre-trained checkpoints following the Steiner et al. (2024) protocol (only learning rate swept, otherwise same transfer settings), compared with PaliGemma 2 on multimodal benchmarks; PaliGemma 2 transferred at 896x896 for the first four benchmarks and 448x448 for the others

Multimodal Google DeepMind — Gemma

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.

Gemma 3
Google DeepMind — Gemma

rich detail 17 method fields published

See how this test was run