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
1.0Rust 17.734.4963,460868  97% 99% 99% 100%
1.1C gcc #9 19.775.1332,240694  95% 96% 100% 96%
1.3C gcc 23.465.8827,932822  100% 100% 100% 100%
1.3C gcc #4 24.076.0530,392799  100% 100% 100% 100%
1.4C gcc #6 24.216.0729,396879  100% 100% 100% 100%
1.4C gcc #3 24.236.0832,516763  100% 100% 100% 100%
1.4C gcc #7 24.246.0932,888994  100% 100% 100% 100%
1.4Ada 2005 GNAT #3 24.146.0932,0041805  99% 99% 100% 99%
1.4C++ g++ #7 24.406.1337,8921017  100% 100% 100% 100%
1.4Rust #2 24.416.2255,7001080  100% 98% 98% 98%
1.4Java  #2 24.246.2788,992796  96% 97% 97% 98%
1.4Go #3 25.596.4432,184894  100% 99% 99% 100%
1.6C++ g++ #6 28.087.0532,9041035  100% 100% 100% 100%
1.6Java  #6 27.967.1688,976802  97% 97% 99% 97%
1.6Scala #4 27.977.2093,120786  97% 100% 97% 96%
1.8Lisp SBCL 28.537.9055,6722459  82% 100% 98% 83%
1.8C# Mono #4 31.588.1280,680872  100% 97% 97% 97%
1.8C# Mono #6 31.628.1282,052986  97% 97% 100% 97%
1.9C++ g++ #9 33.018.5833,620726  95% 95% 100% 95%
2.0Clojure #7 32.409.02152,9761195  89% 86% 97% 88%
2.1F# Mono #4 35.979.4087,616869  96% 95% 97% 96%
2.3Go #2 41.9810.5534,720837  99% 100% 100% 100%
2.6F# Mono #3 44.8311.4880,376800  97% 100% 97% 97%
2.6Haskell GHC #2 45.8111.4941,208782  100% 100% 100% 100%
2.6C# Mono #3 45.1811.5180,128701  98% 98% 100% 98%
2.6Java  #3 45.5011.5389,208903  100% 99% 98% 98%
2.6C# Mono 46.0911.7480,360798  98% 98% 98% 99%
2.6Go #6 46.9711.8433,192700  99% 99% 99% 99%
2.7C++ g++ #8 33.0712.2333,648742  99% 36% 37% 100%
2.9F# Mono #2 48.5512.9651,4001043  93% 96% 92% 94%
2.9Scala 51.1812.9766,852724  98% 98% 99% 100%
3.1OCaml 54.8913.785,492710  100% 100% 100% 100%
3.2Clojure #6 52.6614.36132,0881077  90% 91% 91% 95%
3.5Scala #5 43.6815.8889,196589  87% 71% 67% 51%
3.8Pascal Free Pascal #4 68.1417.0731,160748  100% 100% 100% 100%
4.0Lisp SBCL #3 46.5718.1846,084888  92% 40% 93% 32%
4.2Racket #4 73.7018.6569,588796  99% 99% 100% 99%
4.2Fortran Intel #4 49.0818.7861,076611  94% 41% 93% 34%
4.7Dart 56.8821.0095,528901  98% 37% 99% 37%
6.1Go 55.6027.4536,268823  51% 2% 100% 53%
6.8Pascal Free Pascal 80.5930.3432,456820  91% 40% 95% 41%
7.5Pascal Free Pascal #5 134.9633.8230,044829  100% 100% 100% 100%
8.0C++ g++ #5 36.1236.1333,384590  1% 100% 0% 0%
8.6C++ g++ #2 38.6538.6633,728687  0% 0% 100% 1%
9.6Java  43.0543.0139,336665  2% 99% 0% 1%
11C gcc #2 47.3447.35800400  1% 0% 100% 1%
11Clojure #5 51.5350.13115,3601077  49% 5% 47% 3%
12Scala #2 51.9051.8345,592454  0% 1% 100% 0%
12Ada 2005 GNAT #2 53.1153.131,928572  0% 1% 100% 1%
12OCaml #6 54.9855.00960444  1% 0% 100% 1%
13C# Mono #2 56.2956.3140,200484  100% 0% 0% 0%
13Fortran Intel #5 56.8656.8832,580508  1% 1% 0% 100%
17Racket #3 75.3675.3431,120797  0% 1% 40% 60%
17Pascal Free Pascal #3 75.4475.478530  0% 1% 100% 0%
18Hack #2 80.9881.00117,520458  0% 69% 31% 0%
19C++ g++ #3 83.3483.361,504414  100% 0% 1% 0%
19Racket #2 85.6085.5920,696585  0% 29% 0% 72%
24Racket 107.53107.5221,832517  1% 0% 100% 0%
29Erlang HiPE #2 8 min131.961,370,444613  95% 95% 96% 95%
32Erlang HiPE 8 min142.801,714,956534  92% 92% 94% 92%
53Python 3 #7 15 min239.6042,456686  100% 100% 100% 100%
55Hack 248.01248.09115,560441  4% 15% 52% 31%
68PHP #3 20 min5 min115,240863  100% 100% 100% 100%
98Python 3 #2 28 min7 min10,488777  100% 99% 99% 99%
108Erlang #2 31 min8 min1,312,428613  99% 99% 99% 99%
110Ruby #5 32 min8 min62,6361019  100% 100% 100% 100%
110Erlang 32 min8 min1,643,216534  98% 98% 98% 98%
113Ruby #2 33 min8 min135,564925  99% 99% 100% 99%
115Python 3 #5 34 min8 min40,268449  100% 100% 100% 100%
131Ruby #6 37 min9 min300,384909  95% 95% 95% 95%
171Perl 51 min12 min43,400579  100% 100% 100% 100%
189Ruby JRuby #4 55 min14 min762,944866  98% 98% 98% 98%
216Ruby JRuby #5 1h 02 min16 min1,597,2281019  98% 98% 98% 98%
243Ruby JRuby #3 18 min18 min660,288307  21% 30% 33% 19%
271PHP 20 min20 min4,268443  23% 18% 35% 27%
388Ruby JRuby #2 1h 53 min29 min758,280925  99% 99% 98% 99%
423Ruby #3 31 min31 min7,104307  20% 25% 44% 13%
427Ruby #4 31 min31 min69,156866  21% 29% 31% 20%
Fortran Intel #2 Bad Output813
Fortran Intel #3 Bad Output754
Fortran Intel Bad Output485
Hack #3 Failed864
Pascal Free Pascal #2 Make Error817
Ruby JRuby #6 Failed909
Scala #3 Failed796
"wrong" (different) algorithm / less comparable programs
0.4C gcc #5 7.341.8517,0201026
0.6C++ g++ 10.522.6429,4641239
0.9C gcc #8 16.934.2432,496859
6.8Python 3 #6 119.8130.7854,1521380

 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