Skip to content

Evaluation

DUDE (document VQA)

Document VQA benchmark based on multi-industry, multi-domain, multi-page documents with extractive, abstractive and unanswerable questions; ANLS metric

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