Dataset · mirobody
Metabolic Medical Agent Benchmark
mirobody/MetAgentBench
Interactive clinical benchmark for evaluating AI agents in metabolic medicine and GLP-1 therapy.
What's inside
The dataset contains interactive clinical cases in English and Chinese based on published case reports. The agent must gather patient history, order tests considering cost, and make decisions at each stage. The dataset size is less than 1,000 examples.
What you can do with it
- Evaluating and testing clinical AI agents in endocrinology
- Developing clinical decision support systems for metabolic therapy
- Tasks
- Question answering
- Languages
- English, Chinese
- Size
- up to 1K rows
- Downloads this month
- 3K
- Likes
- 6
How to load it
from datasets import load_dataset
ds = load_dataset("mirobody/MetAgentBench")