Gemini 1.5
Google DeepMind — Gemini
partial detail 7 method fields published
Evaluation
Flash-8B multimodal benchmark sampling
Initial evaluations of Flash-8B across visual tasks and standard evaluations spanning capabilities and modalities (Table 22), instruction-tuned
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.