logo

SPEED CENTER


How fast is PyPy3.9?

Plot 1: The above plot represents PyPy3.9 (pypy3.9-jit-64) benchmark times normalized to cpython. Smaller is better.

It depends greatly on the type of task being performed. The geometric average of all benchmarks is or times faster than cpython

How has PyPy3.9 performance evolved over time?

Plot 2: Speedup compared to cpython, using the inverse of the geometric average of normalized times, out of benchmarks (see paper on why the geometric mean is better for normalized results).