Saved in:
Bibliographic Details
Main Authors: Zhong, Joey, Zhang, Hao, Southern, Clare, Yang, Jeremy, Wang, Thomas, Jung, Kate, Zhang, Shu, Yarats, Denis, Ho, Johnny, Ma, Jerry
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.11685
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911442576343040
author Zhong, Joey
Zhang, Hao
Southern, Clare
Yang, Jeremy
Wang, Thomas
Jung, Kate
Zhang, Shu
Yarats, Denis
Ho, Johnny
Ma, Jerry
author_facet Zhong, Joey
Zhang, Hao
Southern, Clare
Yang, Jeremy
Wang, Thomas
Jung, Kate
Zhang, Shu
Yarats, Denis
Ho, Johnny
Ma, Jerry
contents We present DRACO (Deep Research Accuracy, Completeness, and Objectivity), a benchmark of complex deep research tasks. These tasks, which span 10 domains and draw on information sources from 40 countries, originate from anonymized real-world usage patterns within a large-scale deep research system. Tasks are sampled from a de-identified dataset of Perplexity Deep Research requests, then filtered and augmented to ensure that the tasks are anonymized, open-ended and complex, objectively evaluable, and representative of the broad scope of real-world deep research use cases. Outputs are graded against task-specific rubrics along four dimensions: factual accuracy (accuracy), breadth and depth of analysis (including completeness), presentation quality (including objectivity), and citation quality. DRACO is publicly available at https://hf.co/datasets/perplexity-ai/draco.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11685
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity
Zhong, Joey
Zhang, Hao
Southern, Clare
Yang, Jeremy
Wang, Thomas
Jung, Kate
Zhang, Shu
Yarats, Denis
Ho, Johnny
Ma, Jerry
Machine Learning
Artificial Intelligence
We present DRACO (Deep Research Accuracy, Completeness, and Objectivity), a benchmark of complex deep research tasks. These tasks, which span 10 domains and draw on information sources from 40 countries, originate from anonymized real-world usage patterns within a large-scale deep research system. Tasks are sampled from a de-identified dataset of Perplexity Deep Research requests, then filtered and augmented to ensure that the tasks are anonymized, open-ended and complex, objectively evaluable, and representative of the broad scope of real-world deep research use cases. Outputs are graded against task-specific rubrics along four dimensions: factual accuracy (accuracy), breadth and depth of analysis (including completeness), presentation quality (including objectivity), and citation quality. DRACO is publicly available at https://hf.co/datasets/perplexity-ai/draco.
title DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.11685