mint-bench

by xingyaoww · Agent Tool · ★ 133

About mint-bench

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback Official Repo for paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang\, Zihan Wang\, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng and Heng Ji. MINT benchmark aims to evaluate LLMs' ability to solve tasks with multi-turn interactions by (1) using tools and (2) leveraging natural language feedback. :trophy: Please visit our website for the leaderboard. :warning: WARNING: Evaluation of LLMs requires executing untrusted model-generated code.

Quick Facts

Stars133
Forks8
LanguagePython
CategoryAgent Tool
LicenseApache-2.0
Quality Score67.1695507218813/100
Last Updated2024-06-04
Created2023-09-18
Platformspython
Est. Tokens~4821k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is mint-bench?

mint-bench is Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng and Hen. It is categorized as a Agent Tool with 133 GitHub stars.

What programming language is mint-bench written in?

mint-bench is primarily written in Python.

How do I install or use mint-bench?

You can find installation instructions and usage details in the mint-bench GitHub repository at github.com/xingyaoww/mint-bench. The project has 133 stars and 8 forks, indicating an active community.

What license does mint-bench use?

mint-bench is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools