Dev Builds » 20240521-2006

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 06:53:43 584110 4002 1443 644 1915 +70.31 ± 5.02 4 139 922 926 10 +145.66 ± 11.17
ncm-dbt-02 06:53:11 586055 4014 1504 644 1866 +75.61 ± 5.04 0 142 877 974 14 +156.19 ± 11.48
ncm-dbt-03 06:52:34 586888 4000 1502 600 1898 +79.72 ± 4.99 2 120 865 1000 13 +166.45 ± 11.55
ncm-dbt-04 06:53:26 571019 4012 1472 622 1918 +74.74 ± 5.07 2 144 874 974 12 +155.01 ± 11.5
ncm-dbt-05 06:53:54 584192 3972 1454 640 1878 +72.22 ± 4.99 3 134 900 944 5 +150.87 ± 11.31
20000 7375 3150 9475 +74.52 ± 2.25 11 679 4438 4818 54 +154.79 ± 5.1

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
385740 ncm-dbt-01 586139 2 1 0 1 +189.7 ± 55.98 0 0 0 1 0 +1129.65 ± 376.02
385739 ncm-dbt-02 582903 14 6 4 4 +49.92 ± 120.64 0 1 4 1 1 +49.98 ± 184.5
385738 ncm-dbt-04 571551 12 3 2 7 +29.01 ± 98.94 0 1 3 2 0 +58.45 ± 226.57
385737 ncm-dbt-05 582277 472 180 73 219 +80.15 ± 15.1 0 20 89 127 0 +169.88 ± 36.26
385736 ncm-dbt-03 584369 500 191 85 224 +74.79 ± 14.2 1 14 115 118 2 +155.54 ± 31.67
385735 ncm-dbt-01 584874 500 180 87 233 +65.38 ± 14.42 0 21 117 110 2 +132.54 ± 31.5
385734 ncm-dbt-04 571471 500 171 72 257 +69.71 ± 14.73 1 19 112 116 2 +143.89 ± 32.25
385733 ncm-dbt-02 585717 500 194 92 214 +71.88 ± 14.1 0 17 116 115 2 +147.19 ± 31.57
385732 ncm-dbt-05 584034 500 173 70 257 +72.61 ± 13.69 1 12 121 115 1 +152.18 ± 30.64
385731 ncm-dbt-03 584790 500 181 75 244 +74.79 ± 13.76 0 15 115 119 1 +155.54 ± 31.67
385730 ncm-dbt-01 584537 500 179 80 241 +69.71 ± 13.88 0 18 115 117 0 +145.54 ± 31.75
385729 ncm-dbt-04 572396 500 188 72 240 +82.1 ± 13.83 0 15 104 131 0 +174.55 ± 33.5
385728 ncm-dbt-02 582485 500 184 77 239 +75.52 ± 14.23 0 18 108 123 1 +157.24 ± 32.87
385727 ncm-dbt-05 583782 500 193 77 230 +82.1 ± 13.68 0 14 106 130 0 +174.55 ± 33.13
385726 ncm-dbt-01 583824 500 179 69 252 +77.7 ± 14.58 0 18 107 122 3 +158.93 ± 33.03
385725 ncm-dbt-03 588600 500 184 66 250 +83.57 ± 13.56 0 13 106 131 0 +178.11 ± 33.1
385724 ncm-dbt-04 568832 500 182 77 241 +74.06 ± 14.6 0 21 104 124 1 +153.86 ± 33.54
385723 ncm-dbt-02 587962 500 185 67 248 +83.57 ± 14.45 0 18 97 134 1 +176.33 ± 34.76
385722 ncm-dbt-05 581860 500 174 83 243 +63.95 ± 14.37 1 20 116 113 0 +134.15 ± 31.65
385721 ncm-dbt-03 586985 500 198 72 230 +89.48 ± 14.44 0 16 94 138 2 +189.0 ± 35.33
385720 ncm-dbt-01 585759 500 174 91 235 +58.21 ± 14.53 0 24 121 103 2 +116.78 ± 30.96
385719 ncm-dbt-04 569989 500 187 98 215 +62.51 ± 14.31 0 22 118 109 1 +127.76 ± 31.37
385718 ncm-dbt-02 583908 500 191 80 229 +78.43 ± 14.74 0 19 104 124 3 +160.64 ± 33.54
385717 ncm-dbt-05 583279 500 183 73 244 +77.7 ± 13.25 0 9 125 113 3 +158.93 ± 29.79
385716 ncm-dbt-01 578877 500 182 81 237 +71.16 ± 13.79 0 15 121 112 2 +145.54 ± 30.73
385715 ncm-dbt-04 572517 500 179 73 248 +74.79 ± 14.06 0 18 108 124 0 +157.24 ± 32.87
385714 ncm-dbt-03 587579 500 190 82 228 +76.25 ± 14.53 0 18 109 120 3 +155.54 ± 32.7
385713 ncm-dbt-02 587707 500 191 87 222 +73.33 ± 14.3 0 19 109 121 1 +152.18 ± 32.72
385712 ncm-dbt-05 585337 500 182 96 222 +60.36 ± 14.35 0 24 116 110 0 +124.6 ± 31.69
385711 ncm-dbt-01 584664 500 183 77 240 +74.79 ± 14.06 2 12 114 122 0 +160.64 ± 31.79
385710 ncm-dbt-03 587452 500 179 62 259 +82.83 ± 14.44 1 15 101 132 1 +176.33 ± 34.04
385709 ncm-dbt-04 571672 500 193 78 229 +81.36 ± 14.68 0 19 99 130 2 +169.27 ± 34.4
385708 ncm-dbt-02 588047 500 181 84 235 +68.27 ± 13.83 0 17 120 112 1 +140.62 ± 30.95
385707 ncm-dbt-05 584369 500 178 90 232 +61.79 ± 14.27 1 20 119 110 0 +129.35 ± 31.2
385706 ncm-dbt-01 583405 500 182 93 225 +62.51 ± 14.03 2 14 128 105 1 +130.94 ± 29.72
385705 ncm-dbt-03 588132 500 184 90 226 +66.1 ± 13.6 0 15 128 105 2 +134.15 ± 29.68
385704 ncm-dbt-02 589924 500 187 74 239 +79.9 ± 14.21 0 16 107 125 2 +165.8 ± 33.0
385703 ncm-dbt-04 572316 500 182 74 244 +76.25 ± 13.96 1 12 117 118 2 +158.93 ± 31.27
385702 ncm-dbt-02 585843 500 185 79 236 +74.79 ± 14.2 0 17 112 119 2 +153.86 ± 32.2
385701 ncm-dbt-03 587197 500 195 68 237 +90.22 ± 14.16 0 14 97 137 2 +190.85 ± 34.75
385700 ncm-dbt-04 568434 500 187 76 237 +78.43 ± 14.6 0 17 109 120 4 +158.93 ± 32.69
385699 ncm-dbt-05 588600 500 191 78 231 +79.9 ± 13.92 0 15 108 126 1 +167.53 ± 32.81
385698 ncm-dbt-01 584916 500 183 66 251 +82.83 ± 14.14 0 17 99 134 0 +176.33 ± 34.4

Commit

Commit ID c14b69790a62aad89fcc471cde482923dfe57f1e
Author Linmiao Xu
Date 2024-05-21 20:06:17 UTC
Lower smallnet threshold with updated eval divisors Params found after 30k spsa games at 60+0.6, with initial values from 64k spsa games at 45+0.45 First spsa with 64k / 120k games at 45+0.45: https://tests.stockfishchess.org/tests/view/664a561b5fc7b70b8817c663 https://tests.stockfishchess.org/tests/view/664ae88e830eb9f8866146f9 Second spsa with 30k / 120k games at 60+0.6: https://tests.stockfishchess.org/tests/view/664be227830eb9f886615a36 Values found at 10k games at 60+0.6 also passed STC and LTC: https://tests.stockfishchess.org/tests/view/664bf4bd830eb9f886615a72 https://tests.stockfishchess.org/tests/view/664c0905830eb9f886615abf Passed STC: https://tests.stockfishchess.org/tests/view/664c139e830eb9f886615af2 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 69408 W: 18216 L: 17842 D: 33350 Ptnml(0-2): 257, 8275, 17401, 8379, 392 Passed LTC: https://tests.stockfishchess.org/tests/view/664cdaf7830eb9f886616a24 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 35466 W: 9075 L: 8758 D: 17633 Ptnml(0-2): 27, 3783, 9794, 4104, 25 closes https://github.com/official-stockfish/Stockfish/pull/5280 bench 1301287
Copyright 2011–2024 Next Chess Move LLC