Python Interpreters Benchmarks
x64 ArchLinux : AMD® Ryzen 7 4700U®

- all benchmarks - n-body fannkuch-redux meteor-contest fasta fasta-redux fibonacci fib50 spectral-norm reverse-complement mandelbrot k-nucleotide regex-dna pidigits chameneos-redux templates thread-ring binary-trees-redux binary-trees pystone richards iobench jsonbench - all languages - Python 2 PyPy Python 3 Python dev PyPy 3 Jython IronPython Cython Nuitka Shedskin Numba Pyston MicroPython Grumpy Graal RustPython

vs Python 2 PyPy Python 3 Python dev PyPy 3 Jython IronPython Cython Nuitka Shedskin Numba Pyston MicroPython Grumpy Graal RustPython x64 octa-core

 1 : Are the Python dev programs faster? At a glance.

Each chart bar shows, for one unidentified benchmark, how much the fastest Python dev program used compared to the fastest Python 3 program.

(Memory use is only compared for tasks that require memory to be allocated.)

These are not the only compilers and interpreters. These are not the only programs that could be written. These are not the only tasks that could be solved. These are just 10 tiny examples.

 2 : Are the Python dev programs faster? Approximately.

Each table row shows, for one named benchmark, how much the fastest Python dev program used compared to the fastest Python 3 program.

(Memory use is only compared for tasks that require memory to be allocated.)

Python dev used what fraction? used how many times more?
Benchmark	Time	Memory	Code
reverse-complement †		?	±
pidigits	1/2	?	±
k-nucleotide	±	?	±
regex-dna	±	?	±
binary-trees	±		±
fasta-redux	±	?	±
pystone †	±	?	±
fannkuch-redux	±		±
richards	±		±
spectral-norm	±	?	±
jsonbench	±		±
fib50	±		±
meteor-contest	±		±
n-body	±		±
chameneos-redux	±		±
templates	±		±
fasta	±		±
iobench	±		±
thread-ring †	±		±
mandelbrot	±		±

Python dev used what fraction? used how many times more?
Time-used	|-	|---	25%	median	75%	---|	-|
(Elapsed secs)		±	±	±	±	±	±

† possible mismatch - one-core program compared to multi-core program.

± read the measurements and then read the program source code.

 3 : Are the Python dev programs faster? Measurements.

These are not the only tasks that could be solved. These are just 10 tiny examples. These are not the only compilers and interpreters. These are not the only programs that could be written.

For each named benchmark, measurements of the fastest Python dev program are shown for comparison against measurements of the fastest Python 3 program.

Program Source Code	CPU secs	Elapsed secs	Memory KB	Code B	≈ CPU Load
reverse-complement
Python dev	0.01		?	449	†
Python 3	0.02	0.02	?	458	33% 0% 100% 0% 0% 0% 0% 0% †
pidigits
Python dev	0.01	0.02	?	379	33% 100% 0% 0% 0% 0% 0% 0%
Python 3	0.03	0.03	?	379	25% 0% 100% 0% 0% 0% 33% 25%
k-nucleotide
Python dev	0.07	0.05	?	801	0% 0% 80% 0% 20% 20% 33% 0%
Python 3	0.08	0.06	?	801	57% 50% 14% 0% 25% 17% 29% 17%
regex-dna
Python dev	0.03	0.03	?	524	0% 0% 100% 0% 25% 0% 0% 0%
Python 3	0.04	0.04	?	524	0% 100% 0% 0% 25% 0% 0% 20%
binary-trees
Python dev	0.88	0.18	?	741	65% 61% 63% 53% 55% 85% 59% 63%
Python 3	1.03	0.22	3,584	741	81% 62% 55% 57% 64% 57% 62% 57%
fasta-redux
Python dev	0.15	0.15	?	1115	0% 7% 100% 0% 0% 0% 7% 6%
Python 3	0.17	0.17	?	1115	100% 6% 6% 0% 0% 0% 0% 6%
pystone
Python dev	0.10	0.10	?	2300	0% 0% 0% 0% 17% 100% 0% 10% †
Python 3	0.11	0.12	?	2300	100% 8% 0% 0% 0% 0% 0% 0% †
fannkuch-redux
Python dev	4.09	0.57	97,032	894	93% 84% 91% 92% 96% 91% 91% 91%
Python 3	4.72	0.65	99,300	894	91% 97% 91% 91% 85% 92% 91% 93%
richards
Python dev	0.43	0.43	9,620	2434	98% 0% 2% 0% 0% 0% 0% 0%
Python 3	0.49	0.49	11,092	2434	2% 4% 0% 2% 2% 100% 0% 0%
spectral-norm
Python dev	0.10	0.10	?	394	0% 0% 100% 0% 0% 0% 10% 0%
Python 3	0.11	0.11	?	394	100% 0% 0% 0% 0% 0% 8% 0%
jsonbench
Python dev	1.76	1.76	12,888	322	0% 0% 100% 1% 1% 0% 0% 1%
Python 3	2.00	2.00	13,956	322	2% 0% 1% 100% 0% 1% 1% 2%
fib50
Python dev	1.46	1.46	8,540	136	0% 100% 2% 0% 1% 1% 1% 1%
Python 3	1.63	1.64	10,196	136	100% 1% 2% 1% 1% 0% 0% 1%
meteor-contest
Python dev	1.55	1.55	9,512	1443	0% 0% 0% 100% 1% 1% 1% 0%
Python 3	1.70	1.70	10,964	1443	1% 1% 1% 0% 0% 0% 0% 99%
n-body
Python dev	19.42	19.42	8,992	1315	70% 0% 0% 0% 30% 1% 0% 1%
Python 3	20.69	20.70	10,584	1315	1% 0% 0% 0% 0% 100% 0% 1%
chameneos-redux
Python dev	252.58	184.28	13,504	1191	19% 19% 16% 18% 16% 16% 18% 10%
Python 3	275.05	194.31	16,748	1191	11% 14% 14% 14% 17% 21% 18% 22%
templates
Python dev	0.56	0.56	18,356	322	2% 96% 2% 0% 2% 0% 2% 0%
Python 3	0.57	0.58	20,176	322	100% 0% 0% 2% 0% 3% 0% 2%
fasta
Python dev	4.62	2.61	65,972	2016	28% 66% 2% 0% 37% 7% 3% 38%
Python 3	4.91	2.71	65,720	2016	44% 38% 4% 3% 60% 0% 26% 12%
iobench
Python dev	2.99	3.00	8,828	367	0% 0% 100% 0% 2% 0% 0% 1%
Python 3	2.99	3.03	10,512	367	1% 2% 0% 0% 100% 0% 0% 1%
thread-ring
Python dev	0.24	0.28	384	406	10% 10% 7% 93% 4% 0% 0% 0% †
Python 3	0.28	0.28	1,920	406	100% 7% 0% 0% 4% 0% 0% 3% †
mandelbrot
Python dev	33.65	4.39	307,604	3852	97% 96% 97% 94% 97% 97% 96% 97%
Python 3	25.42	3.34	317,300	3852	95% 99% 94% 96% 95% 94% 96% 96%
fibonacci
Python dev	0.49	0.50	9,384	182	0% 0% 0% 100% 2% 0% 6% 0%
	No program
binary-trees-redux
	No programs

† possible mismatch - one-core program compared to multi-core program.

 4 : Are there other Python dev programs for these benchmarks?

Remember - those are just the fastest Python dev and Python 3 programs measured on this OS/machine. Check if there are other implementations of these benchmark programs for Python dev.

Python 2 PyPy Python 3 Python dev PyPy 3 Jython IronPython Cython Nuitka Shedskin Numba Pyston MicroPython Grumpy Graal RustPython

Maybe one of those other Python dev programs is fastest on a different OS/machine.

 5 : Are there other faster programs for these benchmarks?

Remember - those are just the fastest Python dev and Python 3 programs measured on this OS/machine. Check if there are faster implementations of these benchmark programs for other programming languages.

n-body fannkuch-redux meteor-contest fasta fasta-redux fibonacci fib50 spectral-norm reverse-complement mandelbrot k-nucleotide regex-dna pidigits chameneos-redux templates thread-ring binary-trees-redux binary-trees pystone richards iobench jsonbench

Maybe one of those other programs is fastest on a different OS/machine.

 Python dev : the new Python 

  Home   Conclusions   License   Play