PyPy is missing complex support in numpy (on trunk anyway) and numpy.random to run those benchmarks. Those that run:

  fib - roughly the same time as CPython
  parse_int - 10x over CPython which is extrapolating to their python vs julia about 20% slower
  quicksort - 4x faster than cpython much slower than julia.
  pi_sum - 20x faster than cpython, a bit faster than julia?

Those are very unscientific measurments. Both fib and qsort are recursive benchmarks (why would you write qsort recursively??), so I guess the JIT does not have time to kick in (and PyPys support kinda sucks for recursion at least in terms of warmup times).

On a slightly unrelated note - a modified lxml library runs on pypy albeit a lot slower right now.

Cheers, fijal

EDIT: updated formatting