Skip to content

Evaluation

Interleaved image-text generation evaluation (1-shot)

Qualitative 1-shot evaluation of Gemini Ultra generating interleaved sequences of images and text (creative suggestions given two colors), demonstrating native image output without an intermediate language bottleneck

Multimodal Google DeepMind — Gemini

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.

Gemini 1.0
Google DeepMind — Gemini

rich detail 6 method fields published

See how this test was run