You can find the most recent KGQA benchmark numbers from publications here.
$ git clone https://github.com/KGQA/leaderboard.git北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。
:helicopter: 保险行业语料库，聊天机器人
A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
Dataset and benchmark for RAG on company internal documents.
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI
Repository for MuSiQue: Multi-hop Questions via Single-hop Question Composition, TACL 2022
Data from GitHub · snapshot Sep 24, 2026