ML-Dev-Bench: Comparative Analysis of AI Agents on ML development workflows

TL;DR

ML-Dev-Bench is a comprehensive benchmark designed to evaluate AI agents on real-world machine learning development workflows, covering tasks like dataset management, model training, debugging, and API integration.

Contribution

This work introduces ML-Dev-Bench, the first benchmark to assess AI agents on complete ML development tasks, moving beyond isolated coding challenges.

Findings

ReAct outperforms others in dataset handling.

AIDE shows strengths in debugging tasks.

Openhands demonstrates versatility across multiple stages.

Abstract

In this report, we present ML-Dev-Bench, a benchmark aimed at testing agentic capabilities on applied Machine Learning development tasks. While existing benchmarks focus on isolated coding tasks or Kaggle-style competitions, ML-Dev-Bench tests agents' ability to handle the full complexity of ML development workflows. The benchmark assesses performance across critical aspects including dataset handling, model training, improving existing models, debugging, and API integration with popular ML tools. We evaluate three agents - ReAct, Openhands, and AIDE - on a diverse set of 30 tasks, providing insights into their strengths and limitations in handling practical ML development challenges. We open source the benchmark for the benefit of the community at \href{https://github.com/ml-dev-bench/ml-dev-bench}{https://github.com/ml-dev-bench/ml-dev-bench}.