MMBench

by OpenCompass (Shanghai AI Lab & collaborators)

Editor note

A bilingual (English and Chinese) multiple-choice benchmark that breaks vision-language ability into fine-grained skills, with a scoring method meant to be more robust than single-pass answers.

What it tests: Broad perception and reasoning skills of vision-language models.
Original source: github.com/open-compass/MMBench
Last updated: Repo last commit 2025-05-22
License: Apache-2.0

Facts come only from the linked source (checked 15 Oct 2026). Credit belongs to the creators.

Reviews

No reviews yet.

Reviews from practitioners who sign in with GitHub open soon.