You go too far -- your lack of understanding is simply your lack of understanding ;)
What are you told the table shows?
>> Where does this difference come from? <<
Check the same thing for 2 other language implementations were the arithmetic should be easy. For example, Java median 2.04 and Smalltalk median 21.22 -- the direct comparison shows 11x as the rounded median of the Smalltalk/Java program times.
Seems like your graphs up top in the language versus language comparison need to be reworked to make it clear how bit the difference in reality between x3 and 1/3 is, because right now it is deceptive.
What are you looking at? Perl is shown slower on 3 tasks.
If i calculate the average of the time perl took divided by the time ruby took, i get this:
Which i understand to mean that perl on average took 7% longer.
However if i turn this around i get:
Which i interpret to mean that Ruby took, on average, 58% longer.
These things contradict and i made some mistake here. Can you clear up what i should've been doing?
The table you don't understand shows the median but you seem to be calculating the arithmetic mean.
Or even better: Try to explain in detail why on the overview page perl is claimed to be slower than Ruby, when in a direct comparison it is not.
Also, in addition, after reading your link, the situation seems even worse. Using the median Perl outperforms Ruby by ~15%, but the main site does not reflect that at all.