Aravind Srinivas-led Perplexity AI has launched its own Deep Research tool, which it claims will help users save hours of time by performing in-depth research and analysis on their behalf, while taking less than 3 minutes for most tasks. Perplexity already offered DeepSeek R1 on its platform, and the addition of Deep Research puts it in direct competition with AI giants like OpenAI and Google.
Perplexity says its Pro users will have access to 500 queries per day, while free users will get a limited number of answers. The new AI tool is already available on Perplexity’s website and the company says it will soon be rolled out to iOS, Android and Mac versions of its apps.
In order to use Deep Research, users simply tap on the new option in the model picker below the search box and click on the new option.
How does Perplexity’s Deep Research work?
Perplexity says that its Deep Research tool performs dozens of searches, reads hundreds of sources and reasons what to do next, similar to how a human researcher might approach a topic. Once the source material is complete, the AI agent summarises all the information in a “clear and comprehensive report” that can be exported either as a PDF or as a Perplexity page to share with friends and family.
Perplexity says that Deep Research can help provide ‘expert-level analysis’ on a range of complex topics, including finance, marketing and technology. The company also claims that Deep Research can act as a ‘personal consultant’ in areas such as health, product research and travel planning.
ChatGPT vs Perplexity vs Google: How do the three Deep Research agents fare?
By its own admission, Perplexity lags behind ChatGPT Deep Research in the Humanity’s Last Exam accuracy rankings. However, Perplexity claims that its latest AI offering beats the likes of Gemini Thinking, o3-Mini, Grok 2 and Claude 3.5 Sonnet on the same benchmark.
While Perplexity’s Deep Research may fall short of ChatGPT in terms of accuracy, Srinivas claims in a post that the new AI tool is “an order of magnitude faster and cheaper” than the OpenAI offering. Notably, ChatGPT Deep Research only offers 100 queries to its Pro users, compared to Perplexity’s 500 queries/day for paid users and limited queries for free users.
Meanwhile, the focus on completing most tasks in under 3 minutes is likely a way for Perplexity to undercut ChatGPT Deep Research, which takes anywhere from 30 minutes to several hours for a single query to complete.
While Google was the first to launch a deep research tool based on Gemini 1.5 Pro, the tech giant has now fallen behind Perplexity and ChatGPT, which are powered by more powerful AI models.