handshake-ai-research/bankertoolbench
收藏资源简介:
BankerToolBench是一个包含100个端到端投资银行任务的基准测试,用于评估AI代理。每个任务模拟真实的初级银行家工作——包括构建金融模型、准备推介演示文稿、撰写备忘录——并产生多文件交付物(如Excel、PowerPoint、Word),这些交付物会根据专家制定的评分标准进行评分。该基准测试由来自高盛、摩根大通、Evercore等公司的502名投资银行家共同开发,每个任务的平均人工完成时间为5小时(最长可达21小时),每个任务的平均评分标准为150项。
BankerToolBench is a benchmark of 100 end-to-end investment banking tasks for evaluating AI agents. Each task mirrors real junior-banker work — building financial models, preparing pitch decks, writing memos — and produces multi-file deliverables (Excel, PowerPoint, Word) that are scored against expert-authored rubrics. The benchmark was developed with 502 investment bankers from firms including Goldman Sachs, JPMorgan, Evercore, and others. Human completion time averages 5 hours per task (up to 21 hours), and rubrics average 150 criteria per task.




