Agentic-MME Dataset

This is the official dataset for the Agentic-MME benchmark, featured in Hugging Face Daily Papers.

Agentic-MME is a comprehensive benchmark designed to evaluate the abilities of multimodal agents in tool-use, web searching, and multi-step reasoning through visual clues.

Usage

You can load the dataset using the Hugging Face datasets library:

from datasets import load_dataset

dataset = load_dataset("Crystal1047/Agentic-MME")
# To see the first record
print(dataset["train"][0])