Dev Builds » 20230922-1725

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 07:00:52 573392 4000 1382 685 1933 +61.16 ± 4.9 1 155 995 844 5 +125.58 ± 10.71
ncm-dbt-02 07:00:52 578936 4010 1399 692 1919 +61.9 ± 5.06 2 175 949 872 7 +127.02 ± 11.02
ncm-dbt-03 07:00:22 575268 3994 1371 661 1962 +62.43 ± 4.95 2 153 982 853 7 +128.17 ± 10.79
ncm-dbt-04 07:00:47 560449 4016 1401 687 1928 +62.43 ± 5.04 2 168 962 866 10 +127.6 ± 10.93
ncm-dbt-05 07:00:44 572894 3980 1395 633 1952 +67.35 ± 4.94 0 144 947 892 7 +138.75 ± 11.0
20000 6948 3358 9694 +63.05 ± 2.23 7 795 4835 4327 36 +129.39 ± 4.87

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
422873 ncm-dbt-02 586901 202 70 31 101 +67.93 ± 22.16 0 8 46 47 0 +141.49 ± 50.59 ↓
422872 ncm-dbt-04 570029 208 65 43 100 +36.89 ± 20.8 0 11 60 33 0 +74.62 ± 43.25 ↓
422871 ncm-dbt-01 583866 208 82 43 83 +65.92 ± 22.64 0 8 51 43 2 +129.26 ± 47.73 ↓
422870 ncm-dbt-05 582068 202 70 35 97 +60.81 ± 23.84 0 11 45 44 1 +121.7 ± 51.25 ↓
422869 ncm-dbt-03 583531 218 78 48 92 +48.12 ± 21.56 1 9 58 41 0 +101.61 ± 44.45 ↓
422868 ncm-dbt-04 567126 500 170 83 247 +61.07 ± 14.24 0 22 120 107 1 +124.6 ± 31.07 ↓
422867 ncm-dbt-05 584495 500 165 92 243 +51.09 ± 14.45 0 27 124 98 1 +102.97 ± 30.57 ↓
422866 ncm-dbt-01 583321 500 191 94 215 +68.27 ± 13.53 0 15 124 110 1 +140.62 ± 30.27 ↓
422865 ncm-dbt-02 586054 500 165 84 251 +56.78 ± 14.6 0 26 118 105 1 +115.23 ± 31.41 ↓
422864 ncm-dbt-03 583992 500 179 90 231 +62.51 ± 13.74 0 19 123 108 0 +129.35 ± 30.56 ↓
422863 ncm-dbt-04 493669 500 176 80 244 +67.54 ± 15.58 0 27 104 115 4 +134.15 ± 33.51 ↓
422862 ncm-dbt-01 496443 500 169 86 245 +58.21 ± 13.83 0 21 125 104 0 +119.89 ± 30.32 ↓
422861 ncm-dbt-03 509415 500 174 88 238 +60.36 ± 13.93 0 19 128 101 2 +121.46 ± 29.83 ↓
422860 ncm-dbt-05 503702 500 175 83 242 +64.66 ± 14.53 0 24 110 116 0 +134.15 ± 32.59 ↓
422859 ncm-dbt-02 524297 500 177 92 231 +59.64 ± 15.25 1 27 109 112 1 +123.02 ± 32.74 ↓
422858 ncm-dbt-03 584537 276 90 38 148 +66.25 ± 18.89 0 11 64 63 0 +137.7 ± 42.73 ↓
422857 ncm-dbt-05 578218 278 101 46 131 +69.65 ± 18.97 0 10 65 63 1 +142.46 ± 42.32 ↓
422856 ncm-dbt-01 582569 292 102 55 135 +56.41 ± 18.54 0 14 71 61 0 +115.97 ± 40.5 ↓
422855 ncm-dbt-04 568832 308 112 61 135 +58.07 ± 17.93 2 8 81 63 0 +124.66 ± 37.31 ↓
422854 ncm-dbt-02 585590 308 117 49 142 +77.99 ± 17.09 0 7 73 73 1 +161.95 ± 39.54 ↓
422853 ncm-dbt-03 584537 500 172 82 246 +63.23 ± 14.61 0 24 113 112 1 +129.35 ± 32.14 ↓
422852 ncm-dbt-05 585211 500 175 75 250 +70.44 ± 13.47 0 15 120 115 0 +147.19 ± 30.88 ↓
422851 ncm-dbt-01 585590 500 169 87 244 +57.5 ± 14.08 0 22 125 102 1 +116.78 ± 30.34 ↓
422850 ncm-dbt-04 568593 500 173 88 239 +59.64 ± 14.04 0 19 130 98 3 +118.33 ± 29.54 ↓
422849 ncm-dbt-02 584579 500 171 89 240 +57.5 ± 14.49 1 22 122 104 1 +118.33 ± 30.8 ↓
422848 ncm-dbt-03 583070 500 180 81 239 +69.71 ± 14.86 1 21 107 120 1 +145.54 ± 33.06 ↓
422847 ncm-dbt-05 575435 500 185 70 245 +81.36 ± 13.19 0 9 119 120 2 +169.27 ± 30.73 ↓
422846 ncm-dbt-04 569071 500 167 84 249 +58.21 ± 14.39 0 25 117 108 0 +119.89 ± 31.55 ↓
422845 ncm-dbt-01 581444 500 167 83 250 +58.93 ± 13.58 0 18 131 100 1 +119.89 ± 29.37 ↓
422844 ncm-dbt-02 584495 500 187 87 226 +70.43 ± 13.32 0 13 125 111 1 +145.54 ± 30.03 ↓
422843 ncm-dbt-03 583154 500 169 89 242 +56.07 ± 13.44 0 18 135 96 1 +113.68 ± 28.8 ↓
422842 ncm-dbt-05 579496 500 164 67 269 +68.27 ± 13.83 0 17 120 112 1 +140.62 ± 30.95 ↓
422841 ncm-dbt-04 568077 500 176 88 236 +61.79 ± 14.27 0 23 116 111 0 +127.76 ± 31.68 ↓
422840 ncm-dbt-01 582945 500 161 71 268 +63.23 ± 13.63 0 18 124 108 0 +130.94 ± 30.38 ↓
422839 ncm-dbt-02 584790 500 169 84 247 +59.64 ± 14.32 0 22 123 103 2 +119.89 ± 30.63 ↓
422838 ncm-dbt-03 581610 500 161 71 268 +63.23 ± 13.48 0 15 132 101 2 +127.76 ± 29.1 ↓
422837 ncm-dbt-05 579289 500 171 93 236 +54.65 ± 13.52 0 20 132 98 0 +112.14 ± 29.29 ↓
422836 ncm-dbt-04 566493 500 190 78 232 +79.17 ± 14.76 0 20 100 128 2 +164.07 ± 34.22 ↓
422835 ncm-dbt-01 583363 500 178 93 229 +59.64 ± 13.76 0 20 125 105 0 +123.02 ± 30.3 ↓
422834 ncm-dbt-02 585885 500 166 88 246 +54.65 ± 14.22 0 25 122 103 0 +112.14 ± 30.83 ↓
422833 ncm-dbt-03 583572 500 168 74 258 +66.1 ± 13.6 0 17 122 111 0 +137.37 ± 30.65 ↓
422832 ncm-dbt-05 588132 500 189 72 239 +82.83 ± 13.39 0 11 112 126 1 +174.55 ± 32.0 ↓
422831 ncm-dbt-04 572155 500 172 82 246 +63.23 ± 12.88 0 13 134 103 0 +130.94 ± 28.7 ↓
422830 ncm-dbt-01 580987 500 163 73 264 +63.23 ± 14.2 1 19 119 111 0 +132.54 ± 31.18 ↓
422829 ncm-dbt-02 587834 500 177 88 235 +62.51 ± 14.58 0 25 111 114 0 +129.35 ± 32.44 ↓

Commit

Commit ID 154b8d3ecb19d0b3fa9ec11cc3a1e666dfe0d2ce
Author Stefan Geschwentner
Date 2023-09-22 17:25:57 UTC
Remove VALUE_KNOWN_WIN. After removing classic evaluation VALUE_KNOWN_WIN is not anymore returned explicit evaluation. So remove and replace it with VALUE_TB_WIN_IN_MAX_PLY. Measurement on my big bench (bench 16 1 16 pos1000.fen) verifies that at least with current net the calculated evaluation lies always in the open interval (-VALUE_KNOWN_WIN, VALUE_KNOWN_WIN). So i consider this a non-functional change. But to be safe i tested this also at LTC as requested by Stephane Nicolet. STC: https://tests.stockfishchess.org/tests/view/64f9db40eaf01be8259a6ed5 LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 455296 W: 115981 L: 116217 D: 223098 Ptnml(0-2): 1415, 50835, 123420, 50527, 1451 LTC: https://tests.stockfishchess.org/tests/view/650bfd867ca0d3f7bbf25feb LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 35826 W: 9170 L: 8973 D: 17683 Ptnml(0-2): 12, 3523, 10645, 3722, 11 closes https://github.com/official-stockfish/Stockfish/pull/4792 Bench: 1603079
Copyright 2011–2025 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy Desktop Version