Re:Code Length Measured in 14 Languages
by btilly on Wednesday November 14, 2012 @01:22PM
(#4784633)
Not the test set in Rosetta Code.
The part of the test set that people have actually provided Mathematica solutions for. There is every reason to believe that people are more likely to provide Mathematica solutions for problems that Mathematica is likely to be good at.
There is no reason to think this looking at the website.
Since he uses median ratios, then a single spectacular ratio will not skew the results.