MT-bench

The dataset used in the paper is MT-bench, which is an LLM-based automated evaluation metric comprising 80 challenging questions.

Data and Resources

Cite this as

Wenxuan Zhou, Ravi Agrawal, Shujian Zhang, Sathish Reddy Indurthi, Sanqiang Zhao, Kaiqiang Song, Silei Xu, Chenguang Zhu (2024). Dataset: MT-bench. https://doi.org/10.57702/fe7w0o4l

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2406.11827
Author Wenxuan Zhou
More Authors
Ravi Agrawal
Shujian Zhang
Sathish Reddy Indurthi
Sanqiang Zhao
Kaiqiang Song
Silei Xu
Chenguang Zhu
Homepage https://huggingface.co/datasets/HuggingFaceH4/mt_bench