StatAILab/DataSciEval

1---2title: DataSciEval3emoji: "📊"4colorFrom: blue5colorTo: green6sdk: static7pinned: true8app_file: index.html9short_description: Benchmark LLMs and agents on real-world data science.10tags:11  - leaderboard12  - evaluation13  - benchmark14  - data-science15  - llm16  - agents17---18 19# DataSciEval: A Data Science Benchmark for LLMs and Agents20 21**DataSciEval** is an open benchmark and interactive leaderboard for evaluating large language models (LLMs) and agents on data science. It covers data science theory and methods as well as end-to-end, real-world data analysis.22 23[Open the live DataSciEval benchmark and leaderboard](https://huggingface.co/spaces/StatAILab/DataSciEval)24 25## What DataSciEval evaluates26 27- Knowledge and reasoning across data science theory.28- Understanding and application of data science methods.29- End-to-end performance on real-world data analysis tasks.30- Comparative performance of large language models and agents.31 32## Explore DataSciEval33 34Use the live Hugging Face Space to explore the benchmark, review published evaluation results, and compare the performance of evaluated LLMs and agents.35 36DataSciEval is maintained by [StatAI Lab](https://huggingface.co/StatAILab).37 38## About this Space39 40This Hugging Face Space serves the DataSciEval website from `index.html`.41 42## Repository structure43 44- `index.html`: Homepage layout, styles, benchmark tables, and interactions.45- `images/`: Figures and task examples used by the homepage.46