Munster's previous report from last December graded both Google Now and Siri with a C+. These July tests grade Siri with a B- and Google Now with a B.
Siri's understanding has been improved significantly, according to the tests. Back in December it correctly interpreted questions 88% of the time. In July it was able to correctly interpret questions 96% of the time.
Both platforms have seen major improvements in comprehension levels. In particular, Siri was found this month to correctly interpret questions 96 percent of the time, up from an 88 percent accuracy rate in tests conducted in December of 2012. Unfortunately, even though Siri heard the question right it provided the wrong answer 16% of the time.
Apple has been reducing its reliance on Google to answer questions. Only 3% of answers contained data from Google. That's down from 27% in December.
"We believe Siri will continue increasing the number of queries it can answer without consulting outside sources," the analyst wrote. "This is important because if Siri consistently directs users to other search engines, they will be more likely to simply use Google/another search engine instead of going through Siri."
Also notable is that Siri has gained the ability to answer questions using two sources of information. For example, a search for a location can provide information from Apple Maps and Wikipedia.
Munster thinks Apple could improve Siri by allowing users to filter and sort results. Google Now gives users the ability to filter results based on price, location, rating and hours.
Take a look at the charts below for more details on the comparison testing.