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 #4 22.3622.3731,616799  1% 0% 0% 100%
1.0C gcc #7 22.9022.9032,944994  1% 0% 0% 100%
1.0C++ g++ #7 22.9522.9633,7281017  0% 1% 1% 100%
1.1C gcc #3 24.8424.8532,400763  1% 0% 0% 100%
1.1C gcc 24.9424.9529,348822  1% 0% 0% 100%
1.1C gcc #6 25.0225.0329,332879  1% 0% 0% 100%
1.1Rust #2 25.6025.6253,4201080  1% 1% 0% 100%
1.2Go #3 27.1027.1135,960894  0% 1% 1% 100%
1.2Java  #2 27.1827.1988,448796  1% 0% 1% 100%
1.2Scala #4 27.2227.24105,996786  0% 1% 0% 100%
1.2C++ g++ #6 27.5627.5732,9521035  0% 1% 0% 100%
1.3Java  #6 28.5928.6088,700802  1% 0% 1% 100%
1.3C gcc #9 29.6129.6231,908694  0% 1% 0% 100%
1.4C# Mono #6 30.6830.6974,944986  1% 0% 0% 100%
1.4C++ g++ #8 30.9430.9533,376742  1% 1% 0% 100%
1.4C++ g++ #9 30.9931.0033,428726  1% 0% 1% 100%
1.4C# Mono #4 31.5031.5174,948872  1% 0% 0% 100%
1.4Ada 2005 GNAT #3 32.2532.2732,1681805  1% 0% 0% 100%
1.5C++ g++ #5 34.1634.1833,132590  1% 1% 1% 100%
1.6Clojure #7 34.9634.99128,2641195  0% 1% 1% 100%
1.6F# Mono #4 36.2136.2380,736869  1% 0% 0% 100%
1.7C++ g++ #2 38.0938.1033,440687  1% 1% 1% 100%
1.9Java  #3 42.2442.2688,596903  1% 0% 1% 100%
1.9Scala #5 43.4243.4486,020589  0% 1% 1% 100%
2.0Java  43.7543.7724,056665  1% 1% 1% 100%
2.0Go #2 44.4944.5133,364837  0% 0% 1% 100%
2.0C# Mono #3 44.9945.0174,604701  0% 0% 1% 100%
2.0F# Mono #3 45.1045.1276,000800  1% 0% 0% 100%
2.1C# Mono 45.9445.9574,412798  1% 1% 0% 100%
2.1Fortran Intel #4 47.7847.8057,848611  1% 1% 1% 100%
2.1Go #6 48.0348.0532,284700  0% 1% 1% 100%
2.2Scala 49.9449.9661,292724  3% 2% 1% 100%
2.2C gcc #2 49.9950.00660400  1% 0% 0% 100%
2.3Scala #2 52.5452.5626,344454  1% 0% 1% 100%
2.4Ada 2005 GNAT #2 53.8053.821,628572  1% 0% 1% 100%
2.5Haskell GHC #2 54.9454.9635,200782  1% 1% 0% 100%
2.5Dart 54.9554.9774,120901  0% 1% 1% 100%
2.5Clojure #5 56.1256.1593,0161069  0% 1% 0% 100%
2.5Fortran Intel #5 56.6756.6932,600508  1% 0% 0% 100%
2.6Clojure #6 57.9257.9492,5641069  1% 1% 1% 100%
3.4Lisp SBCL #3 75.4775.4946,592888  0% 1% 1% 100%
3.4Go 75.8075.8332,152823  0% 1% 1% 100%
3.4Racket #3 76.7676.7921,388797  0% 1% 1% 100%
3.5Racket #4 78.1678.1959,040796  0% 0% 0% 100%
3.5Pascal Free Pascal #3 78.7278.758530  1% 1% 0% 100%
3.6Lisp SBCL 80.2580.2755,9082459  1% 1% 1% 100%
3.7Pascal Free Pascal #2 83.6083.6232,948817  0% 0% 1% 100%
3.7Pascal Free Pascal 83.6083.6332,128820  1% 1% 0% 100%
3.8OCaml 84.9285.071,740710  0% 1% 1% 100%
4.5Racket #2 101.26101.2920,296585  0% 0% 1% 100%
5.2Racket 116.68116.7219,724517  0% 0% 1% 100%
5.7C# Mono #2 128.01128.0639,080484  1% 1% 1% 100%
6.1Pascal Free Pascal #5 135.84135.8831,288829  1% 1% 1% 100%
8.5F# Mono #2 189.26189.3244,3481043  1% 1% 1% 100%
10C++ g++ #3 221.64221.701,148414  1% 1% 1% 100%
13Pascal Free Pascal #4 289.90289.9831,720748  1% 1% 0% 100%
15OCaml #6 5 min5 min860444  1% 1% 1% 100%
27Erlang HiPE #2 9 min9 min699,120613  0% 1% 1% 100%
27Erlang HiPE 10 min10 min723,856534  1% 1% 1% 100%
44Ruby JRuby #3 16 min16 min634,516307  0% 1% 1% 100%
44Ruby JRuby #5 16 min16 min1,369,6761019  1% 1% 1% 100%
45Smalltalk VisualWorks #2 16 min16 min25,720467  1% 1% 1% 100%
46Lua #6 17 min17 min18,044623  0% 1% 1% 100%
48Ruby JRuby #4 18 min18 min2,276,172866  0% 1% 1% 100%
49Python 3 #7 18 min18 min28,612686  1% 1% 0% 100%
49Lua #2 18 min18 min864367  1% 1% 1% 100%
51PHP #3 19 min19 min108,404863  1% 1% 0% 100%
51PHP 19 min19 min3,100443  0% 1% 1% 100%
70Ruby JRuby #2 26 min26 min690,920925  0% 1% 1% 100%
76Python 3 #2 28 min28 min29,868777  1% 1% 0% 100%
103Python 3 #5 38 min38 min28,044449  1% 1% 0% 100%
249C CINT #2 1h 32 min1h 32 min4,860400  0% 0% 0% 100%
Fortran Intel Bad Output485
Fortran Intel #3 Bad Output754
Fortran Intel #2 Bad Output813
JavaScript V8 #2 Bad Output353
Lua Failed353
Perl Failed579
Ruby #3 Timed Out1h 00 min307
Ruby #6 Timed Out1h 00 min909
Ruby #4 Timed Out1h 00 min866
Ruby #2 Timed Out1h 00 min925
Ruby #5 Timed Out1h 00 min1019
Ruby JRuby #6 Failed909
Rust Make Error1323
Scala #3 Failed796
"wrong" (different) algorithm / less comparable programs
0.3C gcc #5 7.607.6016,8281026
0.5C++ g++ 11.1811.1931,9201239
0.7C gcc #8 16.5816.5931,812859
6.8Python 3 #6 152.30152.8150,2081380

 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