a test back in Nov 2006. FF2 + Google's anti-phishing blocklist had 81.54% accuracy, but (a) false positives were not measured, and (b) the Phishtank public feed of bad URLs was used, which is surely used as a data source by Google?
RM114 is a system to examine incoming e-mail, system log streams, data files or other data streams, and to sort, filter, or alter the incoming files or data streams according to the user’s wildest desires.