Stefan Pohl Computer Chess

Latest Website-News (2022/06/26): Ratinglist- and regression-testruns of Stockfish 220620 finished: +3 Elo in ratinglist-testrun and -4 Elo in regression-testrun.

Next ratinglist-testrun: Ethereal 13.75 (result probably on wednesday noon (CEST)) - many thanks to Andrew Grant for providing me a free version of Ethereal for testing, again - much appreciated!

New website-section added: EAS-Ratinglist The Engines Aggressiveness Score of the engines of my SPCC-ratinglist. The EAS-ratinglist shows, how aggressive the engines play. This is the world's first engine-ratinglist not measuring strength of engines but engines's style of play !!! More information on the site.

Stay tuned.

Stockfish VLTC UHO Regression testing (2000 games (10min+3sec) vs Stockfish 15): 

Latest testrun:

Stockfish 220620:  (+522,=1000,-478)= 51.1% = +8 Elo (-4 Elo to previous test)

Best testrun so far:

Stockfish 220515:  (+530,=1021,-449)= 52.0% = +14 Elo (+14 Elo to previous best)

See all results, get more information and download the games: Click on the yellow link above...

SPCC Top Engines Ratinglist (+ regular testing of Stockfish Dev-versions)

Playing conditions:

Hardware: Since 20/07/21 AMD Ryzen 3900 12-core (24 threads) notebook with 32GB RAM. 

Speed: (singlethread, TurboBoost-mode switched off, chess starting position) Stockfish 14.1: 750 kn/s (when 20 games are running simultaneously)

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). Mention, the HERT-set is not an Anti-Draw (UHO or something) opening-set, but a classical, balanced opening-set.

Ponder, Large Memory Pages & learning: Off

Thinking time: 180sec+1000ms (= 3min+1sec) 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).

To avoid distortions in the Ordo Elo-calculation, from now, only 2x Stockfish (latest official release + the latest 2 dev-versions)(all older engine-versions games will be deleted, every time, when a new version was tested). Stockfish's older Elo-results can still be seen in the Elo-diagrams below.

Latest update: 2022/06/26: Stockfish 220620 (+3 Elo to Stockfish 220607)

(Ordo-calculation fixed to Stockfish 15 = 3802 Elo)

See the individual statistics of engine-results here

See the Engines Aggressiveness Score Ratinglist here

Download the current gamebase here

Download the complete game-archive here

NEW See the full ratinglist (without Stockfish dev-versions) from 2020 until today here

(calculating the EAS-Ratings of the full list has a high effort and will be done only from time to time, not after each test)

     Program                    Elo    +    -  Games    Score   Av.Op. Draws

   1 Stockfish 220620 avx2    : 3812    8    8  7000    71.6%   3646   56.4%
   2 Stockfish 220607 avx2    : 3809    8    8  7000    71.3%   3646   57.1%
   3 Stockfish 15 220418      : 3802    7    7  7000    70.5%   3646   58.8%
   4 KomodoDragon 3 avx2      : 3761    7    7 10000    63.0%   3662   64.9%
   5 KomodoDragon 3 MCTS      : 3694    7    7  9000    52.8%   3674   69.0%
   6 Koivisto 8.13 avx2       : 3646    6    6 11000    46.9%   3671   67.9%
   7 Berserk 9 avx2           : 3645    6    6 11000    46.7%   3671   66.0%
   8 Fire 8.NN avx2           : 3613    6    6 12000    46.3%   3643   63.6%
   9 Slow Chess 2.9 avx2      : 3585    7    7 10000    38.0%   3678   59.7%
  10 Stockfish final HCE      : 3578    6    6  9000    47.3%   3598   59.6%
  11 Fire 8.NN MCTS avx2      : 3576    7    7  9000    46.5%   3602   69.2%
  12 Ethereal 13.50 nnue      : 3575    6    6 11000    42.0%   3639   63.9%
  13 Revenge 2.0 avx2         : 3566    6    6  9000    48.9%   3574   69.7%
  14 RubiChess 220223 avx2    : 3553    6    6  9000    50.0%   3552   70.0%
  15 rofChade 3.0 avx2        : 3549    7    7  8000    46.4%   3578   66.8%
  16 Seer 2.5.0 avx2          : 3526    6    6 10000    48.9%   3533   67.6%
  17 Minic 3.22 znver3        : 3456    5    5 10000    57.3%   3403   57.3%
  18 Nemorino 6.00 avx2       : 3456    5    5 11000    54.2%   3424   52.9%
  19 Arasan 23.3 avx2         : 3451    6    6  8000    56.3%   3406   57.8%
  20 Igel 3.1.0 popavx2       : 3450    6    6  8000    41.4%   3512   65.5%
  21 Halogen 10.23.11 avx2    : 3417    6    6  8000    51.6%   3406   58.6%
  22 Clover 3.1 avx2          : 3403    6    6  8000    53.7%   3377   54.7%
  23 Uralochka 3.36c avx2     : 3402    6    6  8000    51.4%   3392   57.2%
  24 Rebel 15x2 avx2          : 3396    6    6  9000    50.9%   3390   56.1%
  25 Tucano 10.00 avx2        : 3380    6    6  9000    52.1%   3365   59.4%
  26 Wasp 5.50 avx            : 3372    6    6  9000    53.6%   3346   53.5%
  27 Fritz 18 nnue avx2       : 3363    6    6  8000    45.9%   3393   54.4%
  28 Coiled 1.1 avx2          : 3352    6    6  8000    45.5%   3384   59.6%
  29 Scorpio 3.0.14d cpu      : 3339    6    6  8000    49.4%   3343   50.6%
  30 Dragon 3 aggressive      : 3310    6    6 10000    47.7%   3326   43.5%
  31 Zahak 10.0 avx           : 3308    6    6  8000    43.5%   3355   48.2%
  32 Marvin 6.0.0 avx2        : 3308    7    7  7000    53.0%   3286   50.9%
  33 Velvet 3.3.0 avx2        : 3307    6    6  9000    45.5%   3340   45.5%
  34 Gogobello 3 avx2         : 3303    6    6  8000    49.7%   3306   52.3%
  35 Combusken 2.0.0 amd64    : 3290    7    7  9000    50.3%   3288   47.7%
  36 Lc0 0.29 dnll 791921     : 3289    7    7  8000    51.8%   3276   46.8%
  37 Weiss 2.0 popc           : 3288    6    6 10000    48.3%   3301   49.0%
  38 Black Marlin 5.0 avx2    : 3281    6    6  9000    46.5%   3307   48.6%
  39 Stash 33.0 popc          : 3249    7    7  9000    45.2%   3283   46.6%
  40 Chiron 5 x64             : 3243    6    6  9000    41.4%   3306   43.0%
  41 Danasah 9.0 avx2         : 3237    6    6  9000    42.9%   3288   46.8%

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!! (Stockfish final HCE is Stockfish 200731, the latest version without neural-net and with HCE (=Hand Crafted Evaluation). This engine is (and perhaps will stay forever?) the strongest HCE (Hand Crafted Eval) engine on the planet. IMHO this makes it very interesting for comparsion.)

Some engines are using a nnue-net based on evals of other engines. I decided to test these engines, too. As far as I know the follwing engines use nnue-nets based on evals of other engines (if I missed an engine, please contact me):

Fire 8.NN, Nemorino 6.00, Gogobello 3, Coiled 1.1 (using Stockfish-eval-based nnue nets or nets directly from Stockfish website). Stockfish since 210615 (using Lc0-based nnue nets). Halogen 10.23.11 using a Koivisto-eval-based net.

Some engine-testruns were aborted, because the engine is too weak (below 3200 SPCC-Elo): LittleGoliath 3.15.3

Below you find a diagram of the progress of Stockfish in my tests since April 2022. 

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).