Dev Builds » 20240113-1840

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 06:54:09 584239 4010 1485 632 1893 +75.05 ± 5.03 1 142 875 977 10 +155.94 ± 11.5
ncm-dbt-02 06:54:33 586173 3998 1424 660 1914 +67.22 ± 5.0 2 148 943 896 10 +138.26 ± 11.04
ncm-dbt-03 06:53:06 587099 4000 1460 649 1891 +71.43 ± 5.12 2 156 884 945 13 +147.19 ± 11.44
ncm-dbt-04 06:53:31 571736 4000 1413 651 1936 +67.0 ± 5.08 0 164 923 900 13 +136.77 ± 11.18
ncm-dbt-05 06:55:28 583745 3992 1405 618 1969 +69.4 ± 4.93 0 132 960 889 15 +141.75 ± 10.9
20000 7187 3210 9603 +70.02 ± 2.25 5 742 4585 4607 61 +143.94 ± 5.01

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
391869 ncm-dbt-01 583740 10 5 3 2 +70.36 ± 79.51 0 0 3 2 0 +147.07 ± 211.27
391868 ncm-dbt-05 585211 492 167 78 247 +63.55 ± 13.79 0 15 130 98 3 +126.81 ± 29.33
391867 ncm-dbt-02 583824 498 190 84 224 +75.1 ± 13.96 0 16 112 120 1 +156.26 ± 32.17
391866 ncm-dbt-03 584874 500 181 84 235 +68.27 ± 15.08 0 26 102 121 1 +140.62 ± 33.84
391865 ncm-dbt-04 574297 500 190 81 229 +76.97 ± 14.13 0 15 114 118 3 +157.24 ± 31.83
391864 ncm-dbt-01 585632 500 185 77 238 +76.25 ± 15.35 1 22 97 128 2 +158.93 ± 34.71
391863 ncm-dbt-05 580862 500 171 82 247 +62.51 ± 14.03 0 20 122 107 1 +127.76 ± 30.73
391862 ncm-dbt-02 585632 500 182 88 230 +66.1 ± 14.45 0 21 116 111 2 +134.15 ± 31.65
391861 ncm-dbt-03 587494 500 187 86 227 +71.16 ± 14.22 0 16 121 109 4 +142.26 ± 30.77
391860 ncm-dbt-01 584706 500 188 80 232 +76.25 ± 15.22 0 23 99 125 3 +155.54 ± 34.37
391859 ncm-dbt-04 572155 500 176 87 237 +62.51 ± 13.59 0 17 128 104 1 +127.76 ± 29.76
391858 ncm-dbt-05 582068 500 176 77 247 +69.71 ± 13.44 0 13 127 108 2 +142.26 ± 29.73
391857 ncm-dbt-02 583656 500 175 79 246 +67.54 ± 13.65 0 16 123 110 1 +138.99 ± 30.46
391856 ncm-dbt-04 570348 500 161 86 253 +52.51 ± 14.79 0 28 121 99 2 +104.49 ± 31.0
391855 ncm-dbt-01 583531 500 183 94 223 +62.51 ± 13.59 0 18 125 107 0 +129.35 ± 30.24
391854 ncm-dbt-03 585337 500 172 79 249 +65.38 ± 14.56 0 23 112 114 1 +134.15 ± 32.28
391853 ncm-dbt-05 582193 500 179 69 252 +77.7 ± 14.58 0 18 107 122 3 +158.93 ± 33.03
391852 ncm-dbt-02 586181 500 171 70 259 +71.16 ± 13.49 0 14 122 113 1 +147.19 ± 30.53
391851 ncm-dbt-04 569270 500 179 73 248 +74.79 ± 14.2 0 15 118 113 4 +150.51 ± 31.19
391850 ncm-dbt-01 584958 500 185 83 232 +71.88 ± 13.81 0 15 120 113 2 +147.19 ± 30.88
391849 ncm-dbt-03 587579 500 191 86 223 +74.06 ± 14.46 0 21 103 126 0 +155.54 ± 33.71
391848 ncm-dbt-05 584159 500 190 79 231 +78.44 ± 13.11 0 11 117 122 0 +165.8 ± 31.17
391847 ncm-dbt-02 585253 500 172 79 249 +65.38 ± 14.0 0 19 120 110 1 +134.15 ± 31.01
391846 ncm-dbt-01 584495 500 193 69 238 +88.0 ± 13.81 0 13 101 135 1 +187.16 ± 33.99
391845 ncm-dbt-03 587707 500 175 82 243 +65.38 ± 14.14 0 20 118 111 1 +134.15 ± 31.33
391844 ncm-dbt-04 570428 500 180 77 243 +72.61 ± 14.83 0 23 102 124 1 +150.51 ± 33.87
391843 ncm-dbt-05 586477 500 172 82 246 +63.23 ± 14.61 0 24 113 112 1 +129.35 ± 32.14
391842 ncm-dbt-02 590524 500 187 91 222 +67.55 ± 14.51 1 19 114 115 1 +140.62 ± 31.94
391841 ncm-dbt-01 583908 500 190 71 239 +84.3 ± 13.42 0 11 110 128 1 +178.11 ± 32.33
391840 ncm-dbt-03 587113 500 191 75 234 +82.1 ± 14.42 0 16 105 126 3 +169.27 ± 33.34
391839 ncm-dbt-04 573406 500 175 77 248 +68.99 ± 14.56 0 22 109 118 1 +142.26 ± 32.74
391838 ncm-dbt-01 582903 500 186 85 229 +71.16 ± 13.93 0 17 116 116 1 +147.19 ± 31.57
391837 ncm-dbt-02 585885 500 181 93 226 +61.79 ± 14.14 0 22 118 110 0 +127.76 ± 31.37
391836 ncm-dbt-03 587834 500 174 83 243 +63.95 ± 13.94 1 16 125 107 1 +132.54 ± 30.2
391835 ncm-dbt-05 580945 500 171 72 257 +69.71 ± 14.03 0 17 119 112 2 +142.26 ± 31.1
391834 ncm-dbt-04 572477 500 169 79 252 +63.23 ± 14.75 0 25 111 113 1 +129.35 ± 32.44
391833 ncm-dbt-02 588430 500 166 76 258 +63.23 ± 14.88 1 21 118 107 3 +127.76 ± 31.37
391832 ncm-dbt-01 584285 500 170 70 260 +70.44 ± 14.62 0 23 104 123 0 +147.19 ± 33.54
391831 ncm-dbt-03 588856 500 189 74 237 +81.37 ± 14.96 1 18 98 131 2 +171.02 ± 34.58
391830 ncm-dbt-04 571511 500 183 91 226 +64.66 ± 13.83 0 19 120 111 0 +134.15 ± 31.01
391829 ncm-dbt-05 588047 500 179 79 242 +70.43 ± 13.76 0 14 125 108 3 +142.26 ± 30.08

Commit

Commit ID eec361f64c7d28ff3a5add64bddc5a96800f7fba
Author mstembera
Date 2024-01-13 18:40:53 UTC
Simplify bad quiets The main difference is that instead of returning the first bad quiet as a good one we fall through. This is actually more correct and simpler to implement. Non regression STC: https://tests.stockfishchess.org/tests/view/659bbb3479aa8af82b964ec7 LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 150944 W: 38399 L: 38305 D: 74240 Ptnml(0-2): 485, 18042, 38298, 18188, 459 Non regression LTC: https://tests.stockfishchess.org/tests/view/659c6e6279aa8af82b9660eb LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 192060 W: 47871 L: 47823 D: 96366 Ptnml(0-2): 144, 21912, 51845, 22010, 119 The cutoff is now -8K instead of -7.5K. -7.5K failed. https://tests.stockfishchess.org/tests/view/659a1f4b79aa8af82b962a0e This was likely a false negative. closes https://github.com/official-stockfish/Stockfish/pull/4975 Bench: 1308279
Copyright 2011–2024 Next Chess Move LLC