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.

    sort sortsort
  ×   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%
1.0Rust 20.145.0956,8241290  98% 99% 100% 99%
1.1Ada 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%
1.2C gcc 24.666.1829,568822  100% 100% 100% 100%
1.2C gcc #6 24.656.1829,064879  100% 100% 100% 100%
1.3Go #3 25.446.3932,276894  100% 100% 100% 100%
1.4Java  #2 28.057.1786,152796  98% 97% 98% 99%
1.4Scala #4 27.967.1789,680786  97% 97% 100% 97%
1.4C++ g++ #6 28.667.1931,9361035  100% 100% 100% 100%
1.6Lisp SBCL 28.567.8460,3322459  95% 87% 99% 85%
1.6C# Mono #6 31.488.0357,260986  99% 98% 98% 98%
1.6C# Mono #4 31.588.0557,116872  98% 98% 99% 98%
1.6Java  #6 31.758.0887,668802  98% 98% 98% 99%
1.7C++ g++ #9 33.088.6032,384726  95% 95% 95% 100%
1.8F# Mono #4 34.118.8564,884869  96% 96% 96% 98%
1.8Clojure #7 32.178.95154,3401195  89% 89% 87% 97%
2.1Go #2 41.7510.4833,484837  100% 100% 100% 100%
2.2Java  #3 43.0410.9484,056903  98% 99% 99% 98%
2.2F# Mono #3 44.4611.3057,408800  98% 99% 98% 99%
2.3C# Mono #3 44.9411.3958,292701  98% 99% 99% 99%
2.3Haskell GHC #2 45.8111.4937,116782  100% 100% 100% 100%
2.3C# Mono 45.8311.6156,416798  98% 99% 99% 99%
2.3Go #6 47.0611.7931,000700  100% 100% 100% 100%
2.5C++ g++ #8 33.3912.3232,388742  36% 36% 100% 100%
2.5Scala 49.8512.6761,240724  100% 99% 99% 99%
2.6Go 51.7412.9632,548823  100% 100% 100% 100%
2.6F# Mono #2 47.7812.9726,7281043  90% 92% 94% 94%
2.8OCaml 55.8814.046,548710  100% 100% 100% 100%
3.0Clojure #6 54.8315.00124,8321069  93% 91% 92% 90%
3.2Scala #5 43.6415.8888,140589  62% 82% 63% 69%
3.4Pascal Free Pascal #4 68.1417.0731,160748  100% 100% 100% 100%
3.6Racket #4 71.6118.1160,436796  99% 99% 100% 99%
3.6Lisp SBCL #3 46.6018.2047,484888  32% 40% 92% 93%
3.7Fortran Intel #4 48.4318.4157,492611  96% 34% 95% 41%
4.2Dart 56.9920.9781,624901  39% 98% 38% 98%
6.0Pascal Free Pascal 80.5930.3432,456820  91% 40% 95% 41%
6.7Pascal Free Pascal #5 134.9633.8230,044829  100% 100% 100% 100%
7.5C++ g++ #5 37.6837.7032,256590  1% 0% 0% 100%
7.9C++ g++ #2 39.5539.5632,328687  99% 1% 1% 1%
8.5Java  42.9342.9035,440665  78% 1% 23% 0%
9.4C gcc #2 47.2347.25396400  0% 1% 0% 100%
10Clojure #5 52.2550.69113,4641069  37% 32% 2% 34%
10Scala #2 51.9451.8628,656454  1% 99% 0% 2%
11C# Mono #2 54.9654.9821,816484  1% 0% 100% 0%
11OCaml #6 56.3456.363,128444  93% 0% 0% 7%
11Fortran Intel #5 56.7856.8032,732508  0% 0% 100% 0%
11Ada 2005 GNAT #2 57.2657.281,232572  1% 1% 100% 0%
15Racket #3 73.8573.8121,040797  5% 1% 95% 0%
15C++ g++ #3 74.5774.601,072414  1% 0% 0% 100%
15Pascal Free Pascal #3 75.4475.478530  0% 1% 100% 0%
15Erlang HiPE 274.0377.841,269,512534  88% 96% 85% 84%
17Hack #2 87.8387.86790,384458  100% 1% 1% 0%
18Racket #2 88.0488.0320,252585  0% 1% 100% 0%
20Racket 102.45102.5917,788517  1% 83% 18% 1%
33Hack 165.93165.98782,224441  0% 1% 1% 100%
64PHP #3 21 min5 min115,808863  100% 100% 100% 100%
93Ruby #5 31 min7 min65,1761019  100% 100% 100% 100%
95Python 3 #2 29 min7 min10,556777  90% 100% 90% 90%
99Python 3 #5 33 min8 min40,728449  100% 100% 100% 100%
99Erlang 32 min8 min1,252,976534  98% 98% 98% 98%
111Ruby #2 37 min9 min162,332925  100% 100% 100% 100%
125Ruby #6 39 min10 min303,748909  96% 96% 96% 96%
165Perl 55 min13 min41,196579  100% 100% 100% 100%
169Ruby JRuby #4 55 min14 min762,944866  98% 98% 98% 98%
193Ruby JRuby #5 1h 02 min16 min1,597,2281019  98% 98% 98% 98%
217Ruby JRuby #3 18 min18 min660,288307  21% 30% 33% 19%
258PHP 21 min21 min4,256443  28% 17% 33% 24%
348Ruby JRuby #2 1h 53 min29 min758,280925  99% 99% 98% 99%
366Ruby #3 30 min30 min7,716307  16% 37% 9% 39%
372Ruby #4 31 min31 min61,016866  32% 18% 17% 34%
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
Scala #3 Failed796
"wrong" (different) algorithm / less comparable programs
0.4C gcc #5 7.321.8516,0801026
0.5C++ 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