Its just a quote a made from the link
"The speed of floating point operations is an important measure of performance for computers in many application domains. It is measured in "megaFLOPS" (million floating-point operations per second), or GigaFLOPS, etc. World-class supercomputer installations are generally rated in Teraflops."
So its just fast at carrying out standard single rates of these floating point tasks, which is basically anything a computer can do involving binary numbers (0's and 1's), which is what a computer works in...
To tell the truth, I don't entirely get it either.
Now get your head around this: