Stefan Pohl Computer Chess

Latest Website-News (2020/02/23): AB-testrun of Stockfish 200215 finished. Nice progress: +8 Elo to Stockfish 200201. +11 Elo to Stockfish 11, now. Next AB-testrun: Komodo 13.3.

NN-longtime testrun Lc0 0.23.3k 591226 (last T59 Net, first testrun of a small 10x128 Net) still running.

Stay tuned.

Stockfish testing

Playing conditions:

Hardware: i7-6700HQ 2.6GHz Notebook (Skylake CPU), Windows 10 64bit, 8GB RAM

Fritzmark: singlethread: 5.3 / 2521 (all engines running on one thread, only), average meganodes/s displayed by LittleBlitzerGUI: Houdini: 2.6 mn/s, Stockfish: 2.2 mn/s, Komodo: 2.0 mn/s

Hash: 512MB per engine

GUI: Since 19/09/11: Cutechess-cli (GUI ends game, when a 5-piece endgame is on the board), before: LittleBlitzerGUI (draw at 170 moves, resign at -700cp)

Tablebases: None for engines, 5 Syzygy for cutechess-cli

Openings: HERT_500 testset (by Thomas Zipproth) (download the file at the "Download & Links"-section or here)

Ponder, Large Memory Pages & learning: Off

Thinking time: 180''+1000ms (= 3'+1'') per game/engine (average game-duration: around  7.5 minutes). One 5000 games-testrun takes about 7 days.The version-numbers of the Stockfish engines are the date of the latest patch, which was included in the Stockfish sourcecode, not the release-date of the engine-file, written backwards (year,month,day))(example: 170526 = May, 26, 2017). Since July, 2018 I use the abrok-compiles of Stockfish again (http://abrok.eu/stockfish), because they are now much faster than before - now only 1.3% slower than BrainFish-compiles. So, there is no reason anymore to not use these "official" development-compiles.

Download BrainFish (and the Cerebellum-Libraries): here

Each Stockfish-version plays 1000 games versus Komodo 13.3, Houdini 6, Fire 7.1, Xiphos 0.5.6, Ethereal 11.53. All engines are running with default-settings.

To avoid distortions in the Ordo Elo-calculation, from now, only 2x Stockfish (latest official release + the latest version) and 1x asmFish and 1x Brainfish are stored in the gamebase (all older engine-versions games will be deleted, every time, when a new version was tested). Stockfish, asmFish and BrainFish older Elo-results can still be seen in the Elo-diagrams below. BrainFish plays always with the latest Cerebellum-Libraries of course, because otherwise BrainFish = Stockfish.

Latest update: 2020/02/23: Stockfish 200215 (+8 Elo to Stockfish 200201)

(Ordo-calculation fixed to Stockfish 11 = 3554 Elo)

See the individual statistics of engine-results here

See the ORDO-rating of the archive-gamebase since 2020 here

Download the current gamebase here

Download the archive-gamebase since 2020 here

     Program                    Elo    +    -   Games   Score   Av.Op.  Draws

   1 BrainFish-2 11 bmi2      : 3604    9    9  5000    81.4 %   3337   35.7 %
   2 Stockfish 200215 bmi2    : 3565    8    8  5000    77.9 %   3337   40.4 %
   3 Stockfish 200201 bmi2    : 3557    8    8  5000    77.2 %   3337   41.7 %
   4 Stockfish 11 200118      : 3554    8    8  6000    78.5 %   3318   39.8 %
   5 Stockfish 10 181129      : 3507    5    5 18000    78.0 %   3275   38.3 %
   6 Stockfish 9 180201       : 3456    8    8  5000    74.9 %   3253   41.7 %
   7 Houdini 6 pext           : 3425    3    3 26000    63.0 %   3321   47.7 %
   8 Komodo 13.1 bmi2         : 3406    4    4 16000    56.3 %   3357   48.5 %
   9 Komodo 13.01 bmi2        : 3402    7    7  5000    57.7 %   3344   53.2 %
  10 Komodo 12.3 bmi2         : 3392    6    6  7000    62.7 %   3294   49.4 %
  11 Komodo 13.2 MCTS         : 3313    6    6  6000    44.1 %   3358   54.2 %
  12 Ethereal 11.75 pext      : 3293    5    5 11000    34.0 %   3425   48.1 %
  13 Xiphos 0.6 bmi2          : 3285    6    6 10000    31.1 %   3441   47.2 %
  14 Fire 7.1 popc            : 3278    3    3 26000    44.4 %   3327   51.3 %
  15 Xiphos 0.5.6 bmi2        : 3269    6    6  8000    41.5 %   3335   54.7 %
  16 Ethereal 11.53 pext      : 3262    5    5 10000    42.9 %   3318   53.2 %
  17 Komodo 12.3 MCTS         : 3256    6    6  7000    42.7 %   3314   46.3 %
  18 Ethereal 11.25 pext      : 3249    7    7  7000    36.8 %   3351   50.1 %
  19 Schooner 2.2 popc        : 3224    7    7  6000    31.3 %   3373   50.3 %
  20 Laser 1.7 bmi2           : 3198    7    7  6000    30.8 %   3351   45.8 %
  21 rofChade 2.2 bmi2        : 3198    8    8  5000    27.8 %   3376   43.9 %
  22 Fizbo 2 bmi2             : 3194    8    8  5000    36.0 %   3306   39.0 %
  23 Fritz 17                 : 3193    7    7  6000    29.4 %   3358   44.2 %
  24 Shredder 13 x64          : 3190    8    8  6000    31.9 %   3340   42.6 %
  25 Defenchess 2.2 popc      : 3186    8    8  5000    26.6 %   3376   41.8 %
  26 Booot 6.3.1 popc         : 3180    8    8  5000    34.0 %   3309   44.1 %
  27 Andscacs 0.95 popc       : 3148    9    9  5000    23.1 %   3372   35.4 %

The version-numbers (180622 for example) of the engines are the date of the latest patch, which was included in the Stockfish sourcecode, not the release-date of the engine-file. Especially the asmFish-engines are often released much later!!

Below you find a diagram of the progress of Stockfish in my tests since the end of 2018. 

And below that diagram, the older diagrams.

You can save the diagrams (as a JPG-picture (in originial size)) on your PC with mouseclick (right button) and then choose "save image"...

The Elo-ratings of older Stockfish dev-versions in the Ordo-calculation can be a little different to the Elo-"dots" in the diagram, because the results/games of new Stockfish dev-versions - when getting part of the Ordo-calculation - can change the Elo-ratings of the opponent engines and that can change the Elo-ratings of older Stockfish dev-versions (in the Ordo-calculation / ratinglist, but not in the diagram, where all Elo-"dots" are the rating of one Stockfish dev-version at the moment, when the testrun of that Stockfish dev-version was finished).