Study compares ChatGPT and Google for search engine performance

Share post:

Preply, a tutoring marketplace for language learning, conducted a recent study that compared the search engine performance of ChatGPT and Google, and the results revealed that ChatGPT polled 15 while Google polled 6.

Preply put ChatGPT and Google’s “intelligence” to the test by asking and analyzing a series of questions. The responses were evaluated using criteria such as context, details, efficiency, functionality, impartiality, and others. Here’s how they both fared.

The study evaluated search engines based on the relevance and quality of their responses using a sample of 50 queries. According to the respondents, ChatGPT provided more comprehensive and accurate responses than Google.

ChatGPT, for example, provided a more detailed response that included a list of the top language learning apps, their features, and user reviews when asked to find the best language learning apps, whereas Google only provided a generic list of language learning apps. When asked to find the best vegan restaurants, ChatGPT returned a list of vegan restaurants with detailed reviews, whereas Google returned a list of vegan restaurants in the area.

The study did not give specific reasons for the respondents’ preferences, but it did suggest that ChatGPT’s advanced natural language processing capabilities may have contributed to its superior performance. ChatGPT is an OpenAI language model that uses machine learning to generate human-like responses to text prompts.

According to the study, while Google is a highly sophisticated search engine that uses advanced algorithms to provide relevant and accurate search results, it may be less effective when answering complex or open-ended questions. ChatGPT, on the other hand, is intended to understand natural language and generate responses similar to those of a human expert.

The sources for this piece include an article in ZDNET.

SUBSCRIBE NOW

Related articles

Tests unable to distinguish AI from human reviews

AI-generated restaurant reviews can now pass the Turing test, successfully fooling both human readers and automated detectors, according...

Zuckerberg shares his vision with investors and Meta stock tanks

In an era where instant gratification is often the norm, Meta CEO Mark Zuckerberg’s strategic pivot towards long-term,...

AI surpasses human benchmarks in most areas: Stanford report

Stanford University’s Institute for Human-Centered Artificial Intelligence (HAI) has published the seventh annual issue of its AI Index...

Microsoft and OpenAI partner to build a $100 Billion AI supercomputer “Stargate”

In a bold stride towards computational supremacy, Microsoft, in partnership with OpenAI, is reported to be laying the...

Become a member

New, Relevant Tech Stories. Our article selection is done by industry professionals. Our writers summarize them to give you the key takeaways