DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu +4 more
2/12/2026

No official code found. Best implementation: LiqiangJing/DSBench (123 stars, last commit 2025-08-17).

Semantic Scholar

Code Implementations(1)

LiqiangJing/DSBenchCommunity71%

[ICLR 2025] DSBench: How Far are Data Science Agents from Becoming Data Science Experts?

12310Python, Jupyter NotebookSep 12, 20241 years agoNOASSERTION
agentbenchmarkdata-sciencelarge-language-models

Similar Papers

Can Neural Networks Learn Implicit Logic from Physical Reasoning?

97% match2026

Are Conventional SNNs Really Efficient? A Perspective from Network Quantization

97% match2026

3DFG-PIFu: 3D Feature Grids for Human Digitization from Sparse Views

86% match2026

Does Label Smoothing Help Deep Partial Label Learning?

81% match1 repo2026

How Does Goal Relabeling Improve Sample Efficiency?

81% match2026

DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo

81% match2026

Cite this paper

@article{jing2026dsbench,
  title  = {DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?},
  author = {Liqiang Jing and Zhehui Huang and Xiaoyang Wang and Wenlin Yao and Wenhao Yu and Kaixin Ma and Hongming Zhang and Xinya Du and Dong Yu},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:603daec2792929965fc79c99b89ff3de78cb1ba7},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/603daec2792929965fc79c99b89ff3de78cb1ba7.svg)](https://codeofpaper.com/paper/603daec2792929965fc79c99b89ff3de78cb1ba7)

Discussion