Jason Dowdell pinged me this morning about an entry he wrote at his blog named Comparing Search Engine Results - My Experiment, where Jason does a detailed non-statistically sound (but good) review of comparing search engine results. Something I am considering doing myself, but in a more objective fashion, if that is possible when testing relevancy.
Here is a snippet of the detailed entry to entice you to click over:
On the "big picture" side of things, it's a bit concerning that Google had the least amount of unique results when compared to the other search engines. I'm guessing this is because the other engines do indeed crawl Google's index to seed their own from time to time and to conduct qualitative checks of their own.
Wish I had more time to comment, looks like good stuff.