Skip to content

Dataset · wulin222

MME-Unify benchmark for multimodal models

wulin222/MME-Unify

Evaluation set of images and English text across 10 tasks and 30 subtasks for testing U-MLLMs.

What's inside

A framework and dataset for the comprehensive evaluation of unified multimodal language models (U-MLLMs). It contains images and English text tasks covering 10 main tasks and 30 subtasks, including VQA and multiple-choice questions. The size of the set is between 1,000 and 10,000 examples.

What you can do with it

  • Comprehensive evaluation and comparison of multimodal models (U-MLLMs)
  • Testing models on visual question answering (VQA) tasks
Tasks
Multiple choice, Question answering, Visual question answering
Languages
English
Size
1K–10K rows
Downloads this month
32.7K
Likes
3

How to load it

from datasets import load_dataset

ds = load_dataset("wulin222/MME-Unify")