The article did update with a benchmark link comparing a couple of models to a fusion io card.

http://www.percona.com/blog/2014/08/12/benchmarking-exflash-...

So the 95%, write latency is 1-1.5 msec for one model, and 2.5-3.5 msec for another model. Maybe representing SLC/MLC flash?

95% read latencies are maybe 350 or 250 usec.