MMBench

A bilingual vision-language multiple-choice benchmark with CircularEval over 20 ability dimensions; English and Chinese Dev and Test splits.

Also known as: MMBench_DEV_EN, MMBench-EN

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorymultimodal
Subcategorybilingual vision-language multiple-choice with CircularEval
Page statusactive
MetricCircularEval accuracy
Directionhigher_is_better
Unit%
Dataset size2948
Dataset licenceApache-2.0
PublisherOpenCompass / Shanghai AI Laboratory, with CUHK, NUS and Zhejiang University

What it measures

MMBench tests whether a vision-language model can answer a multiple-choice question about an image across a taxonomy of perception and reasoning skills, rather than on one downstream task such as captioning or VQA. Questions are written in English and in a matched Chinese translation. Level-1 abilities are Perception and Reasoning; those split into six level-2 groups and twenty level-3 skills. Images plus text; not video.

Task format

Multiple-choice with a single gold option. Free-form model text is mapped to A/B/C/D first by rule matching, then by an LLM choice extractor. Paper v5 uses GPT-4 (gpt-4-0125 by default); the GitHub README still says ChatGPT. CircularEval repeats each N-option item N times with rotated choices; the item counts only if every pass is correct. OpenCompass's in-tree config wraps VLMEvalKit MMBench_DEV_EN only.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub