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

arXiv: https://arxiv.org/abs/2601.13591 · HTML: https://mlsanity.com/paper/2601.13591/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow](https://mlsanity.com/paper/2306.07209/) (2023)
- [DataSciBench: An LLM Agent Benchmark for Data Science](https://mlsanity.com/paper/2502.13897/) (2025)
- [DeepAnalyze: Agentic Large Language Models for Autonomous Data Science](https://mlsanity.com/paper/2510.16872/) (2025)
- [DABstep: Data Agent Benchmark for Multi-step Reasoning](https://mlsanity.com/paper/2506.23719/) (2025)
- [LAMBDA: A Large Model Based Data Agent](https://mlsanity.com/paper/2407.17535/) (2024)
- [DSCodeBench: A Realistic Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2505.15621/) (2025)
- [LLM4DS: Evaluating Large Language Models for Data Science Code Generation](https://mlsanity.com/paper/2411.11908/) (2024)

## Built on by (most cited first, 6 of 6)

- [Benchmarking AI Agents for Addressing Scientific Challenges Across Scales](https://mlsanity.com/paper/2606.12736/) (2026)
- [DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval](https://mlsanity.com/paper/2603.04743/) (2026)
- [StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs](https://mlsanity.com/paper/2606.22977/) (2026)
- [AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis](https://mlsanity.com/paper/2608.17834/) (2026)
- [Skill-based Agentic Evaluation for Real-time Data Science Tasks](https://mlsanity.com/paper/2609.16487/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)

## Abstract (arXiv)

Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-world data science problems, which often span multiple taxonomies and lack standard answers, poses a significant challenge for evaluation. To address this, we introduce DSAEval, a benchmark comprising 641 real-world data science problems grounded in 285 diverse datasets, covering both structured and unstructured data (e.g., image and text). DSAEval incorporates three distinctive features: (1) Multimodal Environment Perception, which enables agents to interpret observations from multiple modalities, including text and vision; (2) Multi-Query Interactions, which mirror the iterative and cumulative nature of real-world data science projects; and (3) Multi-Dimensional Evaluation, which provides a holistic assessment across reasoning, code, and results. We systematically evaluate 13 recent advanced agentic LLMs using DSAEval. Our results show that Claude-Sonnet-4.5 achieves the strongest overall performance, MiMo-V2-Pro and GPT-5.2 lead in duration and step efficiency, respectively, and MiMo-V2-Flash is the most cost-effective. We further demonstrate that multimodal perception consistently improves performance on vision-related tasks, with gains ranging from 2.04% to 11.30%. Overall, while current data science agents perform well on structured data and routine data analysis workflows, substantial challenges remain in unstructured domains. Finally, we offer critical insights and outline future research directions.