tool-eval-bench

Community

Benchmark LLM tool-calling quality across various scenarios

AuthorSeraphimSerapis
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Evaluates the ability of LLMs to call tools correctly and efficiently, identifying issues with tool selection, parameter precision, error handling, and more.

Core Features & Use Cases

  • 69 Scenarios: Tests LLMs across 15 categories, including tool selection, parameter precision, multi-step chains, error recovery, and more.
  • Throughput Benchmark: Measures prefill and token generation speed.
  • Pluggable Accuracy Benchmarks: Integrates external benchmarks like GSM8K, MMLU, and IFEval for accuracy evaluation.
  • Use Case: Use this tool to assess the tool-calling quality of LLMs in various agentic workflows, ensuring they can handle tasks like data retrieval, decision-making, and task orchestration.

Quick Start

Run the benchmark with the following command:

tool-eval-bench --short

Dependency Matrix

Required Modules

httpxpytestruffyaml

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: tool-eval-bench
Download link: https://github.com/SeraphimSerapis/tool-eval-bench/archive/main.zip#tool-eval-bench

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.