mandelbrot benchmark N=16,000

Each chart bar shows how many times slower, one ↓ mandelbrot program was, compared to the fastest program.

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.

     sortsortsort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0C gcc #9 19.445.0231,928694  96% 96% 100% 96%
1.2Ada 2005 GNAT #3 22.755.7532,1041805  99% 99% 99% 99%
1.2C++ g++ #7 23.775.9732,3881017  100% 100% 100% 100%
1.2C gcc #3 24.086.0531,644763  100% 100% 100% 100%
1.2C gcc #4 24.176.0729,104799  100% 100% 100% 100%
1.2C gcc #7 24.246.0931,932994  100% 100% 100% 100%
1.3C gcc #6 24.656.1829,064879  100% 100% 100% 100%
1.3C gcc 24.666.1829,568822  100% 100% 100% 100%
1.4Java  #2 27.847.1162,344796  98% 97% 98% 100%
1.4Java  #6 28.087.1762,432802  98% 97% 98% 99%
1.5Scala #4 28.567.42285,580786  96% 96% 98% 96%
1.5Lisp SBCL 28.567.8460,3322459  95% 87% 99% 85%
1.5C++ g++ #6 28.667.1931,9361035  100% 100% 100% 100%
1.6C# Mono #6 31.488.0357,260986  99% 98% 98% 98%
1.6C# Mono #4 31.588.0557,116872  98% 98% 99% 98%
1.7Clojure #7 32.128.94144,4241195  88% 96% 86% 91%
1.7C++ g++ #9 33.088.6032,384726  95% 95% 95% 100%
1.7C++ g++ #8 33.3912.3232,388742  36% 36% 100% 100%
1.8F# Mono #4 34.118.8564,884869  96% 96% 96% 98%
1.9C++ g++ #5 37.6837.7032,256590  1% 0% 0% 100%
2.0C++ g++ #2 39.5539.5632,328687  99% 1% 1% 1%
2.1Go #2 41.7510.4833,484837  100% 100% 100% 100%
2.2Java  42.9842.9519,576665  1% 1% 0% 99%
2.2Scala #5 43.6515.9183,032589  98% 40% 72% 65%
2.3F# Mono #3 44.4611.3057,408800  98% 99% 98% 99%
2.3C# Mono #3 44.9411.3958,292701  98% 99% 99% 99%
2.4Haskell GHC #2 45.8111.4937,116782  100% 100% 100% 100%
2.4C# Mono 45.8311.6156,416798  98% 99% 99% 99%
2.4Lisp SBCL #3 46.6018.2047,484888  32% 40% 92% 93%
2.4Go #6 47.0611.7931,000700  100% 100% 100% 100%
2.4C gcc #2 47.2347.25396400  0% 1% 0% 100%
2.5F# Mono #2 47.7812.9726,7281043  90% 92% 94% 94%
2.5Scala 48.1912.2254,428724  98% 98% 99% 100%
2.5Fortran Intel #4 48.4318.4157,492611  96% 34% 95% 41%
2.6Java  #3 50.8812.8862,416903  99% 99% 100% 98%
2.7Go 51.7412.9632,548823  100% 100% 100% 100%
2.7Scala #2 51.8951.8023,796454  1% 1% 4% 97%
2.7Clojure #5 52.4150.68119,4441069  4% 83% 7% 21%
2.8Clojure #6 54.5415.28125,4001069  91% 89% 88% 89%
2.8C# Mono #2 54.9654.9821,816484  1% 0% 100% 0%
2.9OCaml 55.8814.046,548710  100% 100% 100% 100%
2.9OCaml #6 56.3456.363,128444  93% 0% 0% 7%
2.9Fortran Intel #5 56.7856.8032,732508  0% 0% 100% 0%
2.9Dart 56.9920.9781,624901  39% 98% 38% 98%
2.9Ada 2005 GNAT #2 57.2657.281,232572  1% 1% 100% 0%
3.5Pascal Free Pascal #4 68.1417.0731,160748  100% 100% 100% 100%
3.7Racket #4 71.6118.1160,436796  99% 99% 100% 99%
3.8Racket #3 73.8573.8121,040797  5% 1% 95% 0%
3.8C++ g++ #3 74.5774.601,072414  1% 0% 0% 100%
3.9Pascal Free Pascal #3 75.4475.478530  0% 1% 100% 0%
4.1Pascal Free Pascal 80.5930.3432,456820  91% 40% 95% 41%
4.5Racket #2 88.0488.0320,252585  0% 1% 100% 0%
5.3Racket 102.45102.5917,788517  1% 83% 18% 1%
6.9Pascal Free Pascal #5 134.9633.8230,044829  100% 100% 100% 100%
14Erlang HiPE 274.0377.841,269,512534  88% 96% 85% 84%
15Hack #2 283.58283.69107,372458  1% 0% 100% 1%
57Ruby JRuby #3 18 min18 min629,772307  24% 31% 29% 19%
66PHP #3 21 min5 min115,808863  100% 100% 100% 100%
67PHP 21 min21 min4,256443  28% 17% 33% 24%
91Python 3 #2 29 min7 min10,556777  90% 100% 90% 90%
96Ruby #3 31 min31 min7,508307  30% 29% 18% 25%
100Erlang 32 min8 min1,252,976534  98% 98% 98% 98%
102Python 3 #5 33 min8 min40,728449  100% 100% 100% 100%
103Ruby #5 33 min8 min70,3481019  100% 100% 100% 100%
108Ruby #4 34 min34 min77,032866  25% 26% 25% 26%
112Ruby #2 36 min9 min179,936925  100% 100% 100% 100%
125Ruby #6 40 min10 min107,864909  96% 96% 95% 96%
170Perl 55 min13 min41,196579  100% 100% 100% 100%
173Ruby JRuby #4 56 min14 min2,262,712866  98% 98% 98% 98%
194Ruby JRuby #5 1h 02 min16 min1,474,9841019  98% 98% 98% 98%
221Hack 1h 11 min1h 11 min86,296441  0% 100% 0% 0%
386Ruby JRuby #2 2h 05 min31 min712,676925  99% 99% 99% 99%
Fortran Intel #2 Bad Output813
Fortran Intel #3 Bad Output754
Fortran Intel Bad Output485
Hack #3 Failed864
Pascal Free Pascal #2 Make Error817
Python 3 #3 Failed304
Ruby JRuby #6 Failed909
Rust Bad Output1386
Scala #3 Failed796
"wrong" (different) algorithm / less comparable programs
0.4C gcc #5 7.321.8516,0801026
0.6C++ g++ 10.742.7027,2881239
0.8C gcc #8 16.014.0231,924859
6.2Python 3 #6 120.6630.9952,1241380

 mandelbrot benchmark : Generate Mandelbrot set portable bitmap file

You can write your own program for this task and contribute to the benchmarks game by following these general instructions.

More specifically:

cmp program output N = 200 with this 5KB output file to check your program is correct before contributing.

We are trying to show the performance of various programming language implementations - so we ask that contributed programs not only give the correct result, but also use the same algorithm to calculate that result.

Mandlebrot output N=200,converted to PNG

Each program should plot the Mandelbrot set [-1.5-i,0.5+i] on an N-by-N bitmap. Write output byte-by-byte in portable bitmap format.

For more information see Eric W. Weisstein, "Mandelbrot Set." From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/MandelbrotSet.html

Thanks to Greg Buchholz for this benchmark.

Revised BSD license

  Home   Conclusions   License   Play