galileo-ai/agent-leaderboard-v2
收藏Hugging Face2025-07-16 更新2025-08-09 收录
下载链接：
https://hf-mirror.com/datasets/galileo-ai/agent-leaderboard-v2
下载链接
链接失效反馈官方服务：
资源简介：
Agent Leaderboard v2是一个企业级AI代理人评估基准，用于模拟真实客户支持场景中的多轮对话。该数据集覆盖了银行、医疗保健、保险、投资和电信五个关键行业，并包含了特定领域的工具定义、用户档案和复杂的多目标场景。
Agent Leaderboard v2 is an enterprise-grade AI agent evaluation benchmark designed to simulate multi-turn conversations in realistic customer support scenarios. It covers five critical industries: banking, healthcare, insurance, investment, and telecom, and includes domain-specific tool definitions, user profiles, and complex multi-goal scenarios.
提供机构：
galileo-ai
