Dev Builds » 20240906-1453

Use this dev build

NCM plays each Stockfish dev build 20,000 times against Stockfish 15. This yields an approximate Elo difference and establishes confidence in the strength of the dev builds.

Summary

Host Duration Avg Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo
ncm-dbt-01 06:51:36 584895 4002 1558 599 1845 +84.91 ± 4.88 1 100 852 1035 13 +178.67 ± 11.62
ncm-dbt-02 06:53:15 587987 4020 1544 592 1884 +83.87 ± 4.95 2 112 840 1044 12 +176.62 ± 11.73
ncm-dbt-03 06:52:06 587980 4000 1509 561 1930 +83.94 ± 5.01 1 116 835 1030 18 +175.22 ± 11.76
ncm-dbt-04 06:50:00 571005 4000 1518 550 1932 +85.78 ± 4.94 2 105 829 1051 13 +181.03 ± 11.8
ncm-dbt-05 06:51:52 585371 3978 1493 576 1909 +81.56 ± 5.0 1 121 839 1016 12 +170.81 ± 11.74
20000 7622 2878 9500 +84.01 ± 2.22 7 554 4195 5176 68 +176.46 ± 5.24

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
375931 ncm-dbt-01 584748 2 1 0 1 +189.7 ± 55.98 0 0 0 1 0 +1129.65 ± 376.02
375930 ncm-dbt-02 587325 20 7 2 11 +88.69 ± 58.16 0 0 5 5 0 +190.78 ± 162.33
375929 ncm-dbt-05 584958 478 188 66 224 +90.68 ± 13.27 0 7 104 127 1 +193.77 ± 33.08
375928 ncm-dbt-03 587028 500 188 62 250 +89.48 ± 14.59 0 15 98 133 4 +185.33 ± 34.57
375927 ncm-dbt-04 571511 500 194 62 244 +93.95 ± 13.92 0 12 96 140 2 +200.24 ± 34.91
375926 ncm-dbt-01 583992 500 196 81 223 +81.36 ± 13.96 0 12 115 119 4 +165.8 ± 31.55
375925 ncm-dbt-02 588089 500 191 75 234 +82.1 ± 14.56 0 17 103 127 3 +169.27 ± 33.7
375924 ncm-dbt-05 585379 500 188 74 238 +80.63 ± 13.94 0 16 104 130 0 +171.02 ± 33.51
375923 ncm-dbt-03 589368 500 189 74 237 +81.36 ± 14.4 0 16 106 125 3 +167.53 ± 33.17
375922 ncm-dbt-04 571070 500 193 69 238 +88.0 ± 14.12 1 12 100 136 1 +189.0 ± 34.18
375921 ncm-dbt-01 583992 500 189 71 240 +83.57 ± 14.01 1 12 106 130 1 +178.11 ± 33.1
375920 ncm-dbt-02 588260 500 182 82 236 +70.44 ± 13.47 0 15 120 115 0 +147.19 ± 30.88
375919 ncm-dbt-05 581818 500 172 83 245 +62.51 ± 15.24 1 25 110 112 2 +127.76 ± 32.59
375918 ncm-dbt-03 587919 500 202 69 229 +94.69 ± 13.62 0 11 96 142 1 +204.07 ± 34.89
375917 ncm-dbt-04 571190 500 205 66 229 +99.2 ± 14.6 1 9 96 138 6 +207.95 ± 34.86
375916 ncm-dbt-01 583489 500 199 68 233 +93.2 ± 13.75 0 11 99 138 2 +198.34 ± 34.31
375915 ncm-dbt-02 589283 500 200 72 228 +90.96 ± 13.72 0 12 99 138 1 +194.57 ± 34.34
375914 ncm-dbt-05 583321 500 182 70 248 +79.17 ± 14.05 0 16 107 126 1 +165.8 ± 33.0
375913 ncm-dbt-03 589582 500 194 73 233 +85.78 ± 14.07 0 14 103 131 2 +179.9 ± 33.65
375912 ncm-dbt-04 570989 500 192 72 236 +85.04 ± 14.05 0 15 101 133 1 +179.9 ± 34.03
375911 ncm-dbt-02 590096 500 194 73 233 +85.78 ± 14.51 1 16 94 139 0 +185.33 ± 35.32
375910 ncm-dbt-01 584790 500 186 79 235 +75.52 ± 14.23 0 18 108 123 1 +157.24 ± 32.87
375909 ncm-dbt-05 588472 500 203 66 231 +97.69 ± 13.66 0 9 98 140 3 +207.95 ± 34.43
375908 ncm-dbt-03 585590 500 182 75 243 +75.52 ± 13.64 0 13 119 116 2 +155.54 ± 30.96
375907 ncm-dbt-04 569270 500 187 79 234 +76.25 ± 14.1 0 16 112 120 2 +157.24 ± 32.18
375906 ncm-dbt-02 586435 500 190 78 232 +79.17 ± 14.05 0 14 113 120 3 +162.35 ± 31.95
375905 ncm-dbt-01 584706 500 195 74 231 +85.78 ± 12.98 0 9 111 130 0 +183.51 ± 32.06
375904 ncm-dbt-05 586139 500 185 73 242 +79.17 ± 13.75 0 14 111 124 1 +165.8 ± 32.28
375903 ncm-dbt-04 570909 500 189 64 247 +88.74 ± 13.83 0 14 97 139 0 +190.85 ± 34.75
375902 ncm-dbt-03 588515 500 179 69 252 +77.71 ± 14.72 1 16 108 122 3 +160.64 ± 32.85
375901 ncm-dbt-01 583950 500 192 74 234 +83.57 ± 13.56 0 13 106 131 0 +178.11 ± 33.1
375900 ncm-dbt-02 587834 500 202 52 246 +107.54 ± 14.05 0 11 81 155 3 +234.38 ± 38.14
375899 ncm-dbt-04 571431 500 171 64 265 +75.52 ± 13.94 0 16 112 121 1 +157.24 ± 32.18
375898 ncm-dbt-05 584243 500 190 65 245 +88.74 ± 14.86 0 19 89 140 2 +187.16 ± 36.25
375897 ncm-dbt-01 586943 500 200 71 229 +91.71 ± 13.88 0 11 102 134 3 +192.71 ± 33.75
375896 ncm-dbt-03 587707 500 185 68 247 +82.83 ± 14.14 0 16 102 131 1 +174.55 ± 33.86
375895 ncm-dbt-02 586985 500 194 81 225 +79.9 ± 13.31 1 8 119 121 1 +169.27 ± 30.73
375894 ncm-dbt-04 571672 500 187 74 239 +79.9 ± 13.16 0 11 115 124 0 +169.27 ± 31.5
375893 ncm-dbt-05 588643 500 185 79 236 +74.79 ± 13.91 0 15 116 117 2 +153.86 ± 31.51
375892 ncm-dbt-01 587452 500 200 81 219 +84.3 ± 14.03 0 14 105 129 2 +176.33 ± 33.3
375891 ncm-dbt-03 588132 500 190 71 239 +84.3 ± 14.18 0 15 103 130 2 +176.33 ± 33.67
375890 ncm-dbt-02 587579 500 184 77 239 +75.52 ± 14.37 0 19 106 124 1 +157.24 ± 33.21

Commit

Commit ID e0bfc4b69bbe928d6f474a46560bcc3b3f6709aa
Author Joost VandeVondele
Date 2024-09-06 14:53:45 UTC
Stockfish 17 Official release version of Stockfish 17 Bench: 1484730 --- Stockfish 17 Today we have the pleasure to announce a new major release of Stockfish. As always, you can freely download it at https://stockfishchess.org/download and use it in the GUI of your choice. Don’t forget to join our Discord server[1] to get in touch with the community of developers and users of the project! *Quality of chess play* In tests against Stockfish 16, this release brings an Elo gain of up to 46 points[2] and wins up to 4.5 times more game pairs[3] than it loses. In practice, high-quality moves are now found in less time, with a user upgrading from Stockfish 14 being able to analyze games at least 6 times[4] faster with Stockfish 17 while maintaining roughly the same quality. During this development period, Stockfish won its 9th consecutive first place in the main league of the Top Chess Engine Championship (TCEC)[5], and the 24th consecutive first place in the main events (bullet, blitz, and rapid) of the Computer Chess Championship (CCC)[6]. *Update highlights* *Improved engine lines* This release introduces principal variations (PVs) that are more informative for mate and decisive table base (TB) scores. In both cases, the PV will contain all moves up to checkmate. For mate scores, the PV shown is the best variation known to the engine at that point, while for table base wins, it follows, based on the TB, a sequence of moves that preserves the game outcome to checkmate. *NUMA performance optimization* For high-end computers with multiple CPUs (typically a dual-socket architecture with 100+ cores), this release automatically improves performance with a `NumaPolicy` setting that optimizes non-uniform memory access (NUMA). Although typical consumer hardware will not benefit, speedups of up to 2.8x[7] have been measured. *Shoutouts* *ChessDB* During the past 1.5 years, hundreds of cores have been continuously running Stockfish to grow a database of analyzed positions. This chess cloud database[8] now contains well over 45 billion positions, providing excellent coverage of all openings and commonly played lines. This database is already integrated into GUIs such as En Croissant[9] and Nibbler[10], which access it through the public API. *Leela Chess Zero* Generally considered to be the strongest GPU engine, it continues to provide open data which is essential for training our NNUE networks. They released version 0.31.1[11] of their engine a few weeks ago, check it out! *Website redesign* Our website has undergone a redesign in recent months, most notably in our home page[12], now featuring a darker color scheme and a more modern aesthetic, while still maintaining its core identity. We hope you'll like it as much as we do! *Thank you* The Stockfish project builds on a thriving community of enthusiasts (thanks everybody!) who contribute their expertise, time, and resources to build a free and open-source chess engine that is robust, widely available, and very strong. We would like to express our gratitude for the 11k stars[13] that light up our GitHub project! Thank you for your support and encouragement – your recognition means a lot to us. We invite our chess fans to join the Fishtest testing framework[14] to contribute compute resources needed for development. Programmers can contribute to the project either directly to Stockfish[15] (C++), to Fishtest[16] (HTML, CSS, JavaScript, and Python), to our trainer nnue-pytorch[17] (C++ and Python), or to our website[18] (HTML, CSS/SCSS, and JavaScript). The Stockfish team [1] https://discord.gg/GWDRS3kU6R [2] https://tests.stockfishchess.org/tests/view/66d738ba9de3e7f9b33d159a [3] https://tests.stockfishchess.org/tests/view/66d738f39de3e7f9b33d15a0 [4] https://github.com/official-stockfish/Stockfish/wiki/Useful-data#equivalent-time-odds-and-normalized-game-pair-elo [5] https://en.wikipedia.org/wiki/Stockfish_(chess)#Top_Chess_Engine_Championship [6] https://en.wikipedia.org/wiki/Stockfish_(chess)#Chess.com_Computer_Chess_Championship [7] https://github.com/official-stockfish/Stockfish/pull/5285 [8] https://chessdb.cn/queryc_en/ [9] https://encroissant.org/ [10] https://github.com/rooklift/nibbler [11] https://github.com/LeelaChessZero/lc0/releases/tag/v0.31.1 [12] https://stockfishchess.org/ [13] https://github.com/official-stockfish/Stockfish/stargazers [14] https://github.com/official-stockfish/fishtest/wiki/Running-the-worker [15] https://github.com/official-stockfish/Stockfish [16] https://github.com/official-stockfish/fishtest [17] https://github.com/official-stockfish/nnue-pytorch [18] https://github.com/official-stockfish/stockfish-web
Copyright 2011–2024 Next Chess Move LLC