Google Bard with Gemini vs ChatGPT: first tests

Google Bard with Gemini vs ChatGPT: first tests

an offer twinWhich took place in recent days, gave new impetus to the competition between chatbots: on the basis of… Google is coolthere is a Pro version of the new multimedia model developed by bigG (not in our country yet) which aims to question the current leadership of ChatGPT In the field. Which is most accurate and effective in responding to requests from users?

Seven Bard Claims with Gemini and ChatGPT

As expected, it is important to note that the latest development of Mountain View’s AI technology is currently not accessible from Italy and in the Italian language, except by resorting to certain workarounds. So let’s consider i First tests Conducted by a reliable newspaper such as Ars Technica.

The editorial team decided to submit to the two Chat bots same Summoned It was used in a comparison dating back to last April, when ChatGPT clearly emerged from the comparison with its head held high. And here they are in translated form. Bracketed is the system that has proven to be the best.

  • Write five original puns (tie);
  • Write a five-line debate between a PowerPC fan and an Intel fan, set around the year 2000 (ChatGPT);
  • If Microsoft’s Windows 11 operating system ships on 3.5-inch floppy disks, how many floppy disks are needed? (cold);
  • Summarize the first three paragraphs of the article into one paragraph (ChatGPT);
  • Who invented video games? (Bard is considering the free version of ChatGPT, otherwise the latter comes with GPT-4 Turbo)
  • Write a two-paragraph creative story about Abraham Lincoln’s invention of basketball (tie);
  • Write a Python script that says Hello World,It then creates an infinitely repeated character string (ChatGPT).
See also  Amazon promotion without VAT, these iPhones are still 18% off

Let’s point out Original source To see all the answers provided by the two artificial intelligences. the Comparison winnerAgain, ChatGPT, but by a smaller margin than that seen from tests last spring, demonstrating the progress Google has made with Bard, especially with the recent introduction of Gemini.

However, the indicator should be evaluated for what it represents: the result of subjective judgments based on a series of claims that do not fully represent the potential of the two technologies. According to what BigG announced during the presentation phase, Gemini has got it Superior performance compared to the best current models, for 30 of 32 academic industry benchmarks used in the context of a large language model.

Leave a Reply

Your email address will not be published. Required fields are marked *