Skip to content

Evaluation

BLINK (visual perception tasks)

14 visual perception tasks solvable by humans quickly but challenging for LLMs (multi-view reasoning, depth estimation, etc.)

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 1.5
Google DeepMind — Gemini

partial detail 8 method fields published

See how this test was run