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

9.9){ return number_format($d); } elseif ($d>0.0){ return number_format($d,1); } else { return " "; } } // PAGE //////////////////////////////////////////////// MkMenuForm($Tests,$SelectedTest,$Langs,NULL); $Row = $Tests[$SelectedTest]; $TestName = $Row[TEST_NAME]; $TestTag = $Row[TEST_TAG]; $TestLink = $Row[TEST_LINK]; list($Succeeded,$Failed,$Special,$Labels,$Ratios) = $Data; unset($Data); $first = 0; $NString = 'N=?'; foreach($Succeeded as $d){ if ($d[DATA_TESTVALUE]>0){ $testValue = (double)$d[DATA_TESTVALUE]; $NString = 'N='.number_format($testValue); break; } } // BEWARE - Hard coded values - BEWARE if ($TestName=='fasta'||$TestName=='k-nucleotide'|| $TestName=='reverse-complement'||$TestName=='regex-dna'){ if ($d[DATA_TESTVALUE] == 25000000) { $NString = '≈240MB '.$NString; } elseif ($d[DATA_TESTVALUE] == 2500000) { $NString = '≈24MB '.$NString; } elseif ($d[DATA_TESTVALUE] == 5000000) { $NString = '≈50MB '.$NString; } elseif ($d[DATA_TESTVALUE] == 1000000) { $NString = '≈10MB '.$NString; } elseif ($d[DATA_TESTVALUE] == 500000) { $NString = '≈5MB '.$NString; } } if ($TestName=='startup'){ $NString = ''; } // Use the table column headers to emphasize the row sort order $CPU_sort_td = 'sort'; $MEM_sort_td = 'sort'; $ELAPSED_sort_td = 'sort'; $GZBYTES_sort_td = 'sort'; if ($Sort=='fullcpu'){ $CPU_sort_td = ' '; $Chart_intro_1 = 'how many times slower'; $Chart_intro_2 = 'program was, compared to the fastest program'; } elseif ($Sort=='kb'){ $MEM_sort_td = ' '; $Chart_intro_1 = 'how many times more Memory'; $Chart_intro_2 = 'program used, compared to the program that used least Memory'; } elseif ($Sort=='elapsed'){ $ELAPSED_sort_td = ' '; $Chart_intro_1 = 'how many times slower'; $Chart_intro_2 = 'program was, compared to the fastest program'; } elseif ($Sort=='gz'){ $GZBYTES_sort_td = ' '; $Chart_intro_1 = 'how many times more Code'; $Chart_intro_2 = 'program used, compared to the program that used least Code'; } if ($CanonicalPage){ echo '

'; } ?>

  benchmark 

Each chart bar shows , one ↓  .

These are not the only programs that could be written. These are not the only compilers and interpreters. These are not the only programming languages.

Column × shows how many times more each program used compared to the benchmark program that used least.

   
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
missing benchmark programs
Python 2 No program
PyPy 2 No program
Python 3 No program
Python development version No program
PyPy 3 No program
Jython No program
IronPython No program
Cython No program
Nuitka No program
Shedskin No program
Numba No program
Pyston No program
MicroPython No program
Grumpy No program
Graal No program
RustPython No program

  benchmark : 

The binary-trees-redux benchmark is another simplistic adaptation of Hans Boehm's GCBench, which in turn was adapted from a benchmark by John Ellis and Pete Kovac.

Heap size has been limited for each program, to 8KB more than that program needs to complete the task.

Revised BSD license

  Home   Conclusions   License   Play