Gemini 1.0
Google DeepMind — Gemini
rich detail 10 method fields published
Evaluation
VQAv2 (visual question answering)
High-level object recognition via captioning/QA; zero-shot evaluation, greedy sampling, no external OCR
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.