作者位次 #4/10ACL 2026Findings· Findings of ACL
D ata S ci B ench: An LLM Agent Benchmark for Data Science
Dan Zhang · Sining Zhoubian · Min Cai · Fengzu Li · Lekang Yang · Wei Wang · Tianjiao Dong · Ziniu Hu · Jie Tang · Yisong Yue
摘要
This paper presents DataSciBench, a comprehensive benchmark for evaluating Large Language Models (LLMs) in data science. Unlike existing benchmarks limited to single task, simple evaluation metrics, and readily available ground truth (GT), DataSciBench is built on curated, natural, and challengin...