Loup Ventures has recently published the result from their annual smart speaker IQ tests that questioned four leading personal assistants.
The study involved 800 questions presented to the AIs with two categories for the result: was the question understood properly, and if the answer is yes, was a correct response provided.
Google Assistant emerged as the clear winner by understanding 100 percent of the questions and providing correct answers to 87.9 percent of them. Apple’s Siri came in second place by understanding 99.6 percent of questions and giving 74.6 percent of correct answers.
Nevertheless, all four products saw an improvement in 2018 with Alexa seeing an increment from 64 percent, Google Assistant from 81 percent, Cortana from 56 percent, and Siri from 52 percent.
In their summary, Loup Ventures revealed that almost all of the AIs misunderstood questions that featured a proper noun, which was usually a local restaurant or town. Additionally, an improvement in both – language processing and voice recognition was noted in all four products.
The study involved 800 questions presented to the AIs with two categories for the result: was the question understood properly, and if the answer is yes, was a correct response provided.
Google Assistant emerged as the clear winner by understanding 100 percent of the questions and providing correct answers to 87.9 percent of them. Apple’s Siri came in second place by understanding 99.6 percent of questions and giving 74.6 percent of correct answers.
Related: Artificial Intelligence: Good Versus Evil (infographic)Amazon’s Alexa ranked third by understanding 99 percent of the questions and answering accurately to 72.5 percent. On the fourth position was Microsoft’s Cortana for understanding 99.4 percent of the queries but giving inappropriate or inaccurate answers to 63.4 percent of the questions.
Nevertheless, all four products saw an improvement in 2018 with Alexa seeing an increment from 64 percent, Google Assistant from 81 percent, Cortana from 56 percent, and Siri from 52 percent.
In their summary, Loup Ventures revealed that almost all of the AIs misunderstood questions that featured a proper noun, which was usually a local restaurant or town. Additionally, an improvement in both – language processing and voice recognition was noted in all four products.
