Today it released the results of that year-long effort. The conclusion: YP beats all search engines when it comes to local relevance of results (as measured by user-satisfaction rating).
This is what the quality raters saw in every case (no brand, only results):
There were asked to rate each query result on a scale from bad to perfect. Presumably this reflected whether the results matched the query and their expectations.
I’ve written up the findings in more detail at Search Engine Land. Do you accept or disbelieve them? If the latter, why?