MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models

Pei Wang, Yanan Wu, Noah Wang, Jiaheng Liu, Xiaoshuai Song +10 more
2/12/2026

No official code found. Best implementation: MTU-Bench-Team/MTU-Bench (60 stars, Apache-2.0, last commit 2025-07-24).

Semantic Scholar

Code Implementations(1)

MTU-Bench-Team/MTU-BenchCommunity74%
Apache-2.0

MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models

603PythonOct 15, 20241 years agoApache-2.0

Cite this paper

@article{wang2026mtubench,
  title  = {MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models},
  author = {Pei Wang and Yanan Wu and Noah Wang and Jiaheng Liu and Xiaoshuai Song and Z. Peng and Ken Deng and Chenchen Zhang and Jiakai Wang and Junran Peng and Ge Zhang and Hangyu Guo and Zhaoxiang Zhang and Wenbo Su and Bo Zheng},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:197fd0dc72180530f66a138ffac7fd35e64ddcd5},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/197fd0dc72180530f66a138ffac7fd35e64ddcd5.svg)](https://codeofpaper.com/paper/197fd0dc72180530f66a138ffac7fd35e64ddcd5)

Discussion