DABStep: Data Agent Benchmark for Multi-step Reasoning

Introducing DABstep, a benchmark of 450+ real-world data analysis tasks to evaluate multi-step reasoning in AI agents. The study finds current top agents reach only about 16% accuracy, underscoring a large gap to reliably tackle real data tasks that mix structured data and unstructured documents.

Source

HuggingFace Blog

Ingéré

04 FÉVR. 2025 · 19:10

Score édito

3.0 / 5