Gene Munster, analyst with Piper Jaffray, has regularly tested and rated Siri’s accuracy in correctly interpreting and answering queries. He has released his latest version of the Siri “report card,” and he says Siri has improved under iOS 7.
Munster, via MacRumors:
The primary improvement between Siri in iOS 6 and iOS 7 came from its performance in noisier areas, where Siri was able to translate better through a noisy environment (94% vs. 83% correct in Aug iOS 6). Based on our testing, iOS 7 Siri’s net ability to answer questions (factors in questions not correctly understood) improved to 79% from 77% in August with iOS 6.
Apple has also been working to reduce Siri’s reliance on competitor Google’s search results, shifting its emphasis to Bing, Wikipedia, and WolframAlpha for their results. This is evidenced in Munster’s most recent results, showing only 4% of Siri’s answers as sourcing from Google, versus 17% of the August testing results, and 27% in December 2012.
Siri was also compared to Google Now in the testing, and Munster’s scoring showed both services in a dead heat, both coming in with a “C+” grade. Siri had held a substantial lead in the testing a year ago.
