CostBench

by JiayuJeff · Agent Tool · ★ 31

About CostBench

CostBench This is the official repository for paper "CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents". 🎯 Project Overview CostBench is a comprehensive benchmark for evaluating multi-turn cost-optimal planning and adaptation capabilities of large language models (LLMs) in tool-using scenarios.

Quick Facts

Stars31
Forks0
LanguagePython
CategoryAgent Tool
Quality Score67.9274844671591/100
Last Updated2026-06-14
Created2025-10-31
Platformspython
Est. Tokens~15k

Compatible Skills

These tools work well together with CostBench for enhanced workflows:

  • ToolShield — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (53%)
  • MCPToolBenchPP — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • Toucan — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • toolbench — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is CostBench?

CostBench is The official code repository for the paper "CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents". It is categorized as a Agent Tool with 31 GitHub stars.

What programming language is CostBench written in?

CostBench is primarily written in Python.

How do I install or use CostBench?

You can find installation instructions and usage details in the CostBench GitHub repository at github.com/JiayuJeff/CostBench. The project has 31 stars and 0 forks, indicating an active community.

View on GitHub → Browse Agent Tool tools