(Credit: Jonathan Kitchen / DigitalVision via Getty Images)
Whenever I have to research a specific topic, I naturally turn to the web. But I don't always have the time to spend hours reading every article out there. Instead, I can ask an AI to tackle much of the initial work for me. A variety of popular AIs offer a Deep Research mode, which performs online research on your behalf. Just submit a request, and the AI searches the web for any relevant information and generates a detailed report, complete with sources.
You can try Deep Research with ChatGPT, Google Gemini, Perplexity AI, and Grok. To put the AIs to the test, I gave each one the same topic to research: How GPS developed from its military origins to the commercial system that we all rely on today. Here’s how each AI fared and which one was my favorite.
ChatGPT
OpenAI’s ChatGPT provides two different versions of Deep Research. One is a full version, which offers an in-depth report that can take as long as 30 minutes to complete. The other is a lightweight version, which creates a shorter and less in-depth report in only a few minutes.
The version used depends on your plan. ChatGPT Plus, Team, and Edu users get 10 full queries and 15 lightweight queries per month, Enterprise users get 10 full queries, Pro users get 125 full and 125 lightweight, and free users get five lightweight. After you hit the limit for the full version, your submissions will automatically switch to the lightweight one.
(Credit: Lance Whitney / OpenAI)To use Deep Research, I opened the ChatGPT website, but you can also use the desktop app (Windows, macOS) or mobile app (iOS, Android). You'll want to stick with the GPT 4o model. I selected the Tools icon and chose Run deep research. I submitted my query about GPS through both the full Deep Research and the lightweight versions by using my Plus subscription in one browser and a free account in another. Both asked me to clarify the kind of analysis I wanted, such as how in-depth it should be, whether or not to include technical details, and if it should cover only US systems or ones around the world.
(Credit: Lance Whitney / OpenAI)After providing more details, ChatGPT started its mission. Along the way, it told me what it was doing as it checked out different websites and fashioned its research. I could also see which online sources it was consulting. Though you can do other things while the AI is working, I felt that watching this play-by-play action offered an interesting look into how ChatGPT operates.
In my testing, the full version took almost 10 minutes to search the web and compile the results, while the lightweight one took around four minutes. It alerted me once it was finished.
The full version served up a detailed and in-depth report that felt just long enough. The information covered the progress of GPS from its early military days to its current commercial use, providing a timeline, a list of the key ways that GPS is used, and a satisfying conclusion. The lightweight one offered a much shorter report with key milestones and dates but little else. Both reports addressed my topic, but the full Deep Research was far superior.
(Credit: Lance Whitney / OpenAI)Google Gemini
Gemini’s Deep Research mode is available to both subscribers and free users. Subscribers get around 20 queries per day, while free users are limited to five queries per month. To try this, I opened to the Gemini website. There is also a mobile app for iOS or Android. To use Deep Research, I clicked the drop-down menu at the upper left that lists the current model. You can choose either the faster 2.0 Flash or the more advanced 2.5 Pro; I went with the latter.
(Credit: Lance Whitney / Google)I typed my query about GPS at the prompt, selected Deep Research, and then submitted the request. Gemini’s Deep Research generated an outline of how it planned to address my topic, which I could revise or approve as is. I gave it my OK, and Gemini took to the web to conduct its research.
(Credit: Lance Whitney / Google)Like ChatGPT, Gemini kept me updated along the way by showing the actions it was taking and the websites it was viewing. The entire process took around eight minutes. The generated report was long and quite in-depth, neatly organized into logical sections with a timeline at the beginning and a table of different GPS systems at the end. The writing was more formal and scholarly than what ChatGPT provided, which may be a plus or minus depending on your preference, but I found the report itself interesting and effective.
(Credit: Lance Whitney / Google)Perplexity AI
Perplexity’s Deep Research tool is accessible to paid subscribers and free users. Pro subscribers get a hefty 500 queries each day, while free users receive five queries per day. To dive in, I signed in to the Perplexity AI website, though apps for iOS, Android, Windows, or macOS are also available. At the prompt, I typed my question, selected the Research button, and then submitted my request.
(Credit: Lance Whitney / Perplexity)I gave Perplexity’s research mode the same GPS topic to investigate. The AI kept me abreast of its mission, showing me which specific areas it was researching and which websites it was consulting. Perplexity took only around three minutes to compile its findings and present its report. The results were acceptable, but they paled in comparison to those from ChatGPT and Gemini. Perplexity’s report was quite short and lacked the depth and analysis provided by the other AIs. As a quick read, it was fine, but I wanted more, and it failed to deliver in that regard.
(Credit: Lance Whitney / Perplexity)Grok
Like ChatGPT, xAI's Grok 3 also offers two flavors for its deep research mode. DeepSearch checks out a vast number of online sources, though not all of them useful or reliable. This mode is also quick at completing its research. DeeperSearch is a more advanced version that consults more high-quality sources, and takes longer to run, but should present a more in-depth report.
Whichever mode you use, the number of queries you’re able to run depends on your plan. X Premium+ subscribers get an unlimited number of queries, while free and Basic users are restricted to 10 DeepSearch queries every 24 hours. X also offers a $30-per-month SuperGrok plan with extended access to DeepSearch and DeeperSearch. Beyond using Grok 3 and DeepSearch directly in X (aka Twitter), you can also try it through the dedicated Grok web page and mobile app (iOS, Android).
(Credit: Lance Whitney / xAI)To get started, I typed my query at the Grok prompt, clicked the download arrow for DeepSearch, and chose between DeepSearch and DeeperSearch. I then submitted my request. Using DeepSearch mode, the AI took only a minute and a half to complete the process. DeeperSearch took a little more than two minutes. The DeepSearch report was informative but short and lacking in any real depth or analysis. The DeeperSearch one was longer and more in-depth but still lacked the detail and analysis I wanted.
(Credit: Lance Whitney / xAI)Who Came Out on Top?
Based on my specific query concerning GPS, which AI performed the best? I give the nod to ChatGPT. Its report was the most thorough and in-depth as well as easy and interesting to read. Gemini took second place with a report that also was in-depth, though not as compelling to read. Of course, this is all based just on one query, so keep that in mind when the next time you need an AI to research a topic for you.


