DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems

Maojun Sun^†, Yifei Xie^†, Yue Wu^†, Ruijian Han, Binyan Jiang, Defeng Sun, Yancheng Yuan, Jian Huang.

EMNLP 2026. Accepted.

† Equal contribution (co-first authors).

Paper

Overview

A real-world data science agent benchmark with 641 tasks across 285 datasets, incorporating multimodal perception, multi-query interactions, and multidimensional evaluation of 13 advanced LLM agents.

All publications & manuscripts →