A new cross-domain benchmark reveals how the leading AI research tools perform on real-world production tasks
Two AI-generated research reports land on your desk before a major decision. Both are polished, confidently written, and well-structured, but they reach different conclusions. Which one do you trust, and how would you even begin to find out? In “DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity,” a team at Perplexity and Jeremy Yang, Assistant Professor of Business Administration at Harvard Business School and affiliate with the Digital Data Design Institute at Harvard (D^3), present a rigorous new benchmark for measuring how well AI deep research systems actually perform on real-world production tasks.
Why This Matters
As we increasingly rely on AI for high-stakes tasks, from brainstorming and research to actual execution, the bottleneck is no longer speed, it’s accuracy. The area where AI performs best, producing polished, well-structured output, is precisely where it’s hardest for a non-specialist to detect errors. For business leaders, DRACO’s task-and-rubric design offers a concrete blueprint for evaluating and choosing research agents: define success criteria, test on representative workloads, and be sure to clarify how you’ll know when it’s wrong.
Bonus
While it seems self-evident that we want the best and most accurate information from AI, that’s actually not always the case. Check out “Explanations on Mute: Why We Turn Away From Explainable AI” to see why.
References
[1] Joey Zhong et al., “DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity,” arXiv preprint arXiv:2602.11685 (2026): 2. https://doi.org/10.48550/arXiv.2602.11685
[2] Zhong et al., “DRACO”: 2.
[3] Zhong et al., “DRACO”: 5.
[4] Zhong et al., “DRACO”: 12.
Link to the D^3 insight article
Link to the research paper
Sign up for our newsletter to stay up to date with D^3 news and research: https://d3.harvard.edu/#join-our-community