Perplexity- an AI-powered search engine that is designed to provide accurate, real-time answers to user queries by leveraging large language models. Perplexity app was also made available for Android and iOS users.
The company has now officially introduced a new Deep Research mode on Perplexity but this feature is currently available for Web only.
Introducing Deep Research on Perplexity.
Deep Research lets you generate in-depth research reports on any topic.
Available to everyone for free—up to 5 queries per day for non-subscribers and 500 queries per day for Pro users. pic.twitter.com/obovx7YEUF
— Perplexity (@perplexity_ai) February 14, 2025
When a user asks a Deep Research question, Perplexity performs dozens of searches and reads hundreds of sources and reasons through the material to autonomously deliver a comprehensive report. Deep Research is made free for all, though non-subscribers get to ask up to 5 queries per day while Pro users can ask 500 queries per day.
To give it a try go to perplexity.ai and select Deep Research from the mode selector in the search box before submitting your query.
How does Deep Research work?
This mode takes only 1-2 minutes to complete the work which would take a human expert many hours to perform.
- Research with Reasoning– Deep Research mode iteratively searches, reads documents, and reasons about what to do next, refining its research plan as it learns more about the subject areas.
- Report writing– Once the source materials have been fully evaluated, the agent then synthesizes all the research into a clear and comprehensive report.
- Export & Share– You can then export the final report to a PDF or document, or convert it into a Perplexity page and share it with colleagues or friends.
Users can go for Deep Research mode to conduct expert-level analysis across a range of complex subject matters like- Finance, marketing, technology, current affairs, health, Biography, travel and more.
It is revealed that Deep Research on Perplexity has attained a 20.5% accuracy score on Humanity’s Last Exam, significantly higher than Gemini Thinking, o3-mini, o1, DeepSeek R1, and many other leading models.
Perplexity’s Deep Research scored 93.9% accuracy on the SimpleQA benchmark while it completes most research tasks in under 3 minutes. Deep Research mode will soon be rolled out to Android, iOS, and Mac.
