Duncan, I've recently done a "quick and dirty" comparison of the T2000 server vs Proliant DL380 G3 (based on 3Ghz Xeons). One Niagara core were approximately 7 to 8 times slower than single Xeon CPU in batch task (huge sorts/aggregates) - that is, you need a parallel factor of eight on this "everywhere cool" server in order to beat single threaded Xeon. That being said - you still can use T2000 for batch jobs _if_ your can parallelize them. Otherwise the performance of a single core is just abysmal at best.
Are these servers up to the job of running a database? It sounds like they might be OK for OLTP, but bad if there is significant batch work.
-- Alexander Fatkulin -- http://www.freelists.org/webpage/oracle-l