Stefan Pohl Computer Chess

private website for chessengine-tests


Latest Website-News (2021/04/17): AB-testrun of Stockfish 210415 finished: -4 Elo to Stockfish 210406. NN-testrun of Lc0 0.27.0 PhoenixStein 1.7 net finished: See the results and download the games in the "NN vs SF testing"- section.

Next NN-testrun: Lc0 0.27.0 J94-100 (retest of this net with latest Lc0-binary)

 

I released my Anti Draw Openings collection. Containing Unbalanced Human Openings V3, Drawkiller V4, NBSC Openings V2 and NBC Openings V2. Learn more in the "Anti Draw Openings"- section or download them right here

 

Some 1000 games quicktests of nnue-nets (SF 210131 default vs. SF 210131 testnet). Latest update: 2021/04/15. Some of the best nets were retested with 3x longer thinkingtime. Look at the results here

Direct download of the strongest net so far (3x longer time) is here

 

Stay tuned.


Stockfish testing

 

Playing conditions:

 

Hardware: Since 20/07/21 AMD Ryzen 3900 12-core (24 threads) notebook with 32GB RAM. Now, 20 games are played simultaneously (!), so from now, each testrun will have 6000 or 7000 games (instead of 5000 before) and will take only 2 days, not 6-7 days as before! From now, all engine-binaries are popcount/avx2, of course, because bmi2-compiles are extremly slow on AMD. To keep the rating-list engine-names consistent, the "bmi2"- or "pext"-extension in the engine-name is still in use for older engines - otherwise ORDO will not calculate all played games by this engine as one engine...

Speed: (singlethread, TurboBoost-mode switched off, chess starting position) Stockfish: 1.3 mn/s, Komodo: 1.1 mn/s

Hash: 256MB per engine

GUI: Cutechess-cli (GUI ends game, when a 5-piece endgame is on the board)

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 7000 games-testrun takes about 2 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: 200807 = August, 7, 2020). The used SF compile is the AVX2-compile, which is the fastest on my AMD Ryzen CPU. SF binaries are taken from abrok.eu (except the official SF-release versions, which are taken form the official Stockfish website).

Download BrainFish (and the Cerebellum-Libraries)here

 

To avoid distortions in the Ordo Elo-calculation, from now, only 3x Stockfish (latest official release + the latest 2 dev-versions) 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 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: 2021/04/17: Stockfish 210415 (-4 Elo to Stockfish 210406)

 

(Ordo-calculation fixed to Stockfish 13 = 3723 Elo)

 

See the individual statistics of engine-results here

Download the current gamebase here

 

     Program                    Elo    +    -   Games   Score   Av.Op.  Draws

   1 Stockfish 210406 avx2    : 3731    7    7  7000    76.9 %   3501   43.9 %
   2 Stockfish 210318 avx2    : 3728    8    8  7000    76.6 %   3501   44.9 %
   3 Stockfish 210415 avx2    : 3727    7    7  7000    76.5 %   3501   45.1 %
   4 CFish 12 3xCerebellum    : 3725    9    9  7000    86.1 %   3388   27.3 %
   5 CFish 210324 avx2        : 3724    7    7  7000    76.2 %   3501   45.1 %
   6 Stockfish 13 210218      : 3723    5    5 17000    69.2 %   3554   57.5 %
   7 SF Fat Fritz 2 avx2      : 3718    7    7  8000    73.7 %   3514   49.3 %
   8 CFish 12 avx2            : 3702    8    8  7000    84.6 %   3388   29.1 %
   9 Stockfish 12 200902      : 3683    4    4 26000    78.7 %   3429   38.5 %
  10 SF Fat Fritz 2 github    : 3678    7    7  7000    73.3 %   3484   48.5 %
  11 SF miniNNUE 210307       : 3658    7    7  7000    69.5 %   3501   51.0 %
  12 KomodoDragon 1.0 avx2    : 3647    4    4 25000    66.6 %   3502   51.0 %
  13 LcFish 210401 avx2       : 3636    7    7  7000    67.2 %   3501   53.5 %
  14 Stockfish 200731 popc    : 3600    8    8  7000    80.5 %   3344   36.2 %
  15 Stockfish 11 200118      : 3563    5    5 17000    69.5 %   3402   41.6 %
  16 Stockfish 10 181129      : 3524    5    5 15000    78.5 %   3287   37.7 %
  17 KomodoDragon 1.0 MCTS    : 3481    6    6  7000    57.6 %   3426   57.1 %
  18 Stockfish 9 180201       : 3474    9    9  5000    74.9 %   3272   41.7 %
  19 Komodo 14.1 x64          : 3454    6    6  8000    56.3 %   3410   55.6 %
  20 Komodo 14 bmi2           : 3444    4    4 18000    52.6 %   3429   51.9 %
  21 Nemorino 6.00 avx2       : 3441    3    3 30000    44.6 %   3491   50.0 %
  22 Houdini 6 pext           : 3439    2    2 61000    53.4 %   3418   46.1 %
  23 Komodo 13.3 bmi2         : 3437    6    6  8000    62.8 %   3341   49.9 %
  24 Fire 8 popc              : 3432    5    5 15000    35.8 %   3554   45.7 %
  25 Komodo 13.1 bmi2         : 3424    6    6 11000    62.0 %   3333   48.8 %
  26 Slow Chess 2.5 avx2      : 3422    4    4 21000    35.7 %   3546   44.8 %
  27 Komodo 12.3 bmi2         : 3411    7    7  7000    62.7 %   3313   49.4 %
  28 Nemorino 6.05 avx2       : 3406    6    6  7000    42.8 %   3468   51.0 %
  29 Ethereal 12.75 avx2      : 3399    3    3 30000    39.5 %   3493   47.9 %
  30 Ethereal 12.62 avx2      : 3390    6    6  8000    49.1 %   3401   54.6 %
  31 Igel 3.0.0 popavx2       : 3386    6    6  7000    36.1 %   3501   52.3 %
  32 Slow Chess 2.4 popc      : 3374    5    5 12000    43.7 %   3427   52.3 %
  33 Ethereal 12.50 popc      : 3356    6    6  7000    45.8 %   3396   55.2 %
  34 RubiChess 2.0 avx2       : 3356    5    5 12000    30.2 %   3527   45.5 %
  35 Slow Chess 2.3 popc      : 3344    5    5 13000    44.2 %   3391   53.8 %
  36 Komodo 14 MCTS           : 3339    7    7  5000    44.4 %   3384   53.4 %
  37 Ethereal 12.25 pext      : 3337    6    6 12000    35.2 %   3470   46.4 %
  38 Pedone 3 avx2            : 3330    6    6  8000    33.4 %   3467   46.7 %
  39 Igel 2.9.0 popavx2       : 3329    5    5 11000    34.5 %   3453   50.1 %
  40 Slow Chess 2.2 popc      : 3328    6    6 11000    32.9 %   3482   42.7 %
  41 RubiChess 1.9dev nnue    : 3320    6    6  8000    31.8 %   3471   45.6 %
  42 Ethereal 12.00 pext      : 3316    6    6  9000    43.1 %   3370   50.8 %
  43 Ethereal 11.75 pext      : 3308    6    6  9000    39.3 %   3391   53.2 %
  44 Xiphos 0.6 bmi2          : 3303    3    3 30000    36.9 %   3414   49.6 %
  45 Fire 7.1 popc            : 3300    3    3 41000    41.9 %   3372   50.7 %
  46 Booot 6.5 popc           : 3293    7    7  7000    25.5 %   3501   39.3 %
  47 Xiphos 0.5.6 bmi2        : 3288    7    7  7000    41.2 %   3355   54.6 %
  48 Minic 2.51 nasc_nutr     : 3283    7    7  7000    31.2 %   3436   45.0 %
  49 Ethereal 11.53 pext      : 3280    7    7  7000    42.2 %   3342   53.4 %
  50 Komodo 12.3 MCTS         : 3275    7    7  7000    42.7 %   3333   46.3 %
  51 Ethereal 11.25 pext      : 3271    7    7  6000    38.4 %   3361   51.0 %
  52 rofChade 2.3 bmi2        : 3257    5    5 11000    33.8 %   3387   47.5 %
  53 Booot 6.4 popc           : 3244    7    7  6000    31.1 %   3393   46.5 %
  54 Schooner 2.2 popc        : 3241    7    7  6000    31.3 %   3390   50.3 %
  55 Laser 1.7 bmi2           : 3218    7    7  6000    30.8 %   3370   45.8 %
  56 Fizbo 2 bmi2             : 3212    8    8  5000    36.0 %   3324   39.0 %
  57 Fritz 17                 : 3212    8    8  6000    29.4 %   3376   44.2 %
  58 Shredder 13 x64          : 3209    7    7  6000    31.9 %   3358   42.6 %
  59 RubiChess 1.8 popc       : 3207    6    6  7000    32.0 %   3344   46.1 %
  60 Defenchess 2.2 popc      : 3205    9    9  5000    26.6 %   3394   41.8 %
  61 Booot 6.3.1 popc         : 3199    9    9  5000    34.0 %   3327   44.1 %
  62 Andscacs 0.95 popc       : 3167    9    9  5000    23.1 %   3390   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 August 2020

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).

 

 

 

 

 

 


Sie sind Besucher Nr.