Gemini 1.5
Google DeepMind — Gemini
partial detail 8 method fields published
Evaluation
V* Benchmark (high-resolution image detail QA)
V* Benchmark (Wu and Xie, 2023): questions about attributes and spatial relations of very small objects on high-resolution images (avg 2246x1582) from SA-1B
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.