DABstep: Data Agent Benchmark for Multi-step Reasoning

TL;DR

DABstep is a new benchmark for testing AI agents on complex, multi-step data analysis tasks using real-world financial data, highlighting current limitations of large language models in this domain.

Contribution

We introduce DABstep, a comprehensive benchmark with over 450 real-world challenges for evaluating multi-step data analysis capabilities of AI agents.

Findings

Leading LLM-based agents achieve only 14.55% accuracy on hardest tasks.

DABstep's design enables scalable, automatic scoring of complex data analysis tasks.

Benchmark release includes a leaderboard and toolkit to foster further research.

Abstract

We introduce DABstep, a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks. DABstep comprises over 450 real-world challenges derived from a financial analytics platform, requiring models to combine code-based data processing with contextual reasoning over heterogeneous documentation. Each task demands an iterative, multi-step problem-solving approach, testing capabilities in data manipulation, cross-referencing multiple sources, and precise result reporting. The benchmark provides a factoid-style answer format with automatic correctness checks for objective scoring at scale. We evaluate leading LLM-based agents, revealing a substantial performance gap: even the best agent achieves only 14.55% accuracy on the hardest tasks. We detail our benchmark's design, dataset composition, task formulation, evaluation protocol, report baseline results and analyze failure modes. DABstep is released with a public leaderboard and toolkit to accelerate research in autonomous data analysis.