Dev Builds » 20221105-0815

You are viewing an old NCM Stockfish dev build test. You may find the most recent dev build tests using Stockfish 15 as the baseline here.

Use this dev build

NCM plays each Stockfish dev build 20,000 times against Stockfish 14. 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 10:06:32 1266701 3340 1352 380 1608 +104.12 ± 5.57 0 82 562 998 28 +222.55 ± 14.38
ncm-dbt-02 09:55:29 1260954 3292 1318 367 1607 +103.31 ± 5.57 0 75 574 968 29 +219.94 ± 14.22
ncm-dbt-03 10:04:48 1300306 3358 1340 372 1646 +103.08 ± 5.47 1 68 602 978 30 +219.5 ± 13.88
ncm-dbt-04 10:06:51 1291544 3338 1336 373 1629 +103.16 ± 5.55 1 74 585 979 30 +219.67 ± 14.09
ncm-dbt-05 10:00:55 1292863 3318 1339 352 1627 +106.57 ± 5.51 1 62 580 981 35 +227.27 ± 14.14
ncm-dbt-06 10:05:28 1287838 3354 1299 378 1677 +97.92 ± 5.54 0 88 603 963 23 +207.7 ± 13.88
20000 7984 2222 9794 +103.01 ± 2.26 3 449 3506 5867 175 +219.36 ± 5.75

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
186745 ncm-dbt-02 1242032 142 57 19 66 +95.29 ± 26.23 0 3 28 39 1 +200.78 ± 65.51 ↓
186744 ncm-dbt-05 1226612 150 62 20 68 +99.94 ± 23.4 0 1 32 41 1 +213.19 ± 59.86 ↓
186743 ncm-dbt-01 1209985 162 67 25 70 +92.17 ± 28.66 0 7 28 43 3 +182.37 ± 65.31 ↓
186742 ncm-dbt-04 1251024 172 68 27 77 +84.44 ± 23.59 0 5 35 46 0 +180.24 ± 58.38 ↓
186741 ncm-dbt-03 1205900 186 75 21 90 +103.85 ± 24.25 0 4 34 52 3 +214.05 ± 59.42 ↓
186740 ncm-dbt-06 1221873 188 69 25 94 +82.85 ± 22.19 0 5 40 49 0 +176.36 ± 54.34 ↓
186739 ncm-dbt-02 1232827 500 200 54 246 +104.49 ± 14.66 0 12 86 146 6 +219.87 ± 36.98 ↓
186738 ncm-dbt-05 1236736 500 196 52 252 +102.97 ± 14.34 0 11 89 145 5 +217.85 ± 36.33 ↓
186737 ncm-dbt-01 1186094 500 218 63 219 +111.37 ± 15.15 0 15 71 158 6 +238.66 ± 40.5 ↓
186736 ncm-dbt-04 1215229 500 209 59 232 +107.54 ± 13.73 0 9 85 153 3 +234.38 ± 37.19 ↓
186735 ncm-dbt-03 1244359 500 202 65 233 +97.69 ± 15.45 0 16 89 137 8 +198.34 ± 36.31 ↓
186734 ncm-dbt-06 1217156 500 183 40 277 +102.22 ± 14.63 0 16 77 155 2 +221.9 ± 38.94 ↓
186733 ncm-dbt-02 1232677 500 207 48 245 +114.45 ± 13.38 0 6 83 157 4 +251.89 ± 37.57 ↓
186732 ncm-dbt-05 1228973 500 207 58 235 +106.77 ± 14.36 0 10 87 147 6 +226.0 ± 36.75 ↓
186731 ncm-dbt-01 1209397 500 196 54 250 +101.46 ± 15.07 0 18 75 154 3 +217.85 ± 39.29 ↓
186730 ncm-dbt-04 1226940 500 195 56 249 +99.2 ± 14.45 0 13 89 144 4 +209.91 ± 36.34 ↓
186729 ncm-dbt-03 1224251 500 205 53 242 +109.07 ± 13.73 0 8 86 152 4 +236.51 ± 36.93 ↓
186728 ncm-dbt-06 1227539 500 198 63 239 +96.19 ± 15.29 0 18 84 143 5 +200.24 ± 37.29 ↓
186727 ncm-dbt-02 1208875 500 195 63 242 +93.95 ± 14.67 0 14 95 136 5 +194.57 ± 35.13 ↓
186726 ncm-dbt-05 1238632 500 194 35 271 +114.45 ± 14.21 0 8 82 153 7 +245.2 ± 37.88 ↓
186725 ncm-dbt-01 1185378 500 200 49 251 +108.3 ± 13.4 0 5 94 146 5 +232.26 ± 35.0 ↓
186724 ncm-dbt-04 1235121 500 204 43 253 +116.0 ± 15.16 1 8 80 151 10 +245.2 ± 38.39 ↓
186723 ncm-dbt-03 1255165 500 191 52 257 +99.2 ± 14.45 0 13 89 144 4 +209.91 ± 36.34 ↓
186722 ncm-dbt-06 1223457 500 191 51 258 +99.95 ± 13.84 0 13 84 153 0 +219.87 ± 37.42 ↓
186721 ncm-dbt-05 1228296 500 212 58 230 +110.6 ± 14.38 0 8 88 146 8 +232.26 ± 36.48 ↓
186720 ncm-dbt-02 1240310 500 199 49 252 +107.54 ± 13.56 0 9 84 155 2 +236.51 ± 37.42 ↓
186719 ncm-dbt-01 1173690 500 195 64 241 +93.2 ± 15.09 0 18 87 141 4 +194.57 ± 36.67 ↓
186718 ncm-dbt-03 1259638 500 197 54 249 +102.22 ± 13.21 0 8 92 149 1 +223.94 ± 35.61 ↓
186717 ncm-dbt-06 1214738 500 204 59 237 +103.73 ± 13.71 0 8 93 145 4 +221.9 ± 35.4 ↓
186716 ncm-dbt-04 1240468 500 190 51 259 +99.2 ± 15.04 0 16 84 145 5 +207.95 ± 37.36 ↓
186715 ncm-dbt-05 1210825 500 207 49 244 +113.68 ± 13.55 0 7 82 157 4 +249.64 ± 37.86 ↓
186714 ncm-dbt-02 1234637 500 201 66 233 +96.19 ± 14.71 0 15 89 142 4 +202.15 ± 36.32 ↓
186713 ncm-dbt-01 1205840 500 198 47 255 +108.3 ± 13.73 0 8 87 151 4 +234.38 ± 36.71 ↓
186712 ncm-dbt-03 1242600 500 196 52 252 +102.97 ± 13.87 0 9 92 145 4 +219.87 ± 35.65 ↓
186711 ncm-dbt-06 1229246 500 192 59 249 +94.69 ± 14.09 0 10 102 133 5 +196.45 ± 33.71 ↓
186710 ncm-dbt-04 1221537 500 200 52 248 +106.01 ± 14.2 0 11 84 151 4 +228.08 ± 37.44 ↓
186709 ncm-dbt-05 1245135 500 199 50 251 +106.78 ± 14.36 1 9 84 152 4 +232.26 ± 37.43 ↓
186708 ncm-dbt-02 1247607 500 199 55 246 +102.97 ± 14.18 0 12 85 150 3 +221.9 ± 37.21 ↓
186707 ncm-dbt-03 1232452 500 207 55 238 +109.07 ± 13.89 1 6 87 152 4 +238.66 ± 36.67 ↓
186706 ncm-dbt-06 1213276 500 197 61 242 +96.94 ± 14.72 0 13 94 137 6 +200.24 ± 35.32 ↓
186705 ncm-dbt-04 1217777 500 209 66 225 +102.22 ± 14.02 0 10 91 145 4 +217.85 ± 35.89 ↓
186704 ncm-dbt-01 1172447 500 203 52 245 +108.3 ± 13.23 0 6 90 151 3 +236.51 ± 35.94 ↓
175371 ncm-dbt-05 1434439 10 3 3 4 0.0 ± 6.81 0 0 5 0 0 0.0 ± 6.09 ↓
175370 ncm-dbt-06 1442535 8 3 0 5 +136.8 ± 89.09 0 0 1 3 0 +337.69 ± 541.44 ↓
175369 ncm-dbt-03 1448958 14 5 2 7 +75.56 ± 67.89 0 0 4 3 0 +159.09 ± 177.81 ↓
175368 ncm-dbt-01 1439052 12 6 1 5 +154.02 ± 64.21 0 0 1 5 0 +416.21 ± 496.36 ↓
175367 ncm-dbt-04 1436169 10 4 1 5 +107.43 ± 84.35 0 0 2 3 0 +240.65 ± 570.11 ↓
175365 ncm-dbt-04 1434292 6 2 1 3 +58.33 ± 98.71 0 0 2 1 0 +120.24 ± 264.77 ↓
175364 ncm-dbt-03 1441805 8 4 1 3 +136.8 ± 89.09 0 0 1 3 0 +337.69 ± 541.44 ↓
175363 ncm-dbt-06 1443992 8 3 1 4 +88.67 ± 172.94 0 1 0 3 0 +190.79 ± 663.13 ↓
175362 ncm-dbt-05 1439786 8 4 1 3 +136.8 ± 89.09 0 0 1 3 0 +337.69 ± 541.44 ↓
175361 ncm-dbt-01 1443987 16 8 2 6 +136.89 ± 61.78 0 0 2 6 0 +337.87 ± 515.83 ↓
175360 ncm-dbt-02 1448670 150 60 13 77 +112.64 ± 29.25 0 4 24 43 4 +226.69 ± 71.37 ↓
175359 ncm-dbt-06 1444570 150 59 19 72 +94.94 ± 26.23 0 4 28 42 1 +200.24 ± 65.72 ↓
175358 ncm-dbt-03 1447934 150 58 17 75 +97.44 ± 27.2 0 4 28 41 2 +200.24 ± 65.72 ↓
175357 ncm-dbt-04 1436887 150 55 17 78 +89.97 ± 23.18 0 2 33 40 0 +193.95 ± 59.26 ↓
175356 ncm-dbt-01 1441145 150 61 23 66 +89.97 ± 26.07 0 5 27 43 0 +193.95 ± 66.93 ↓
175355 ncm-dbt-05 1439204 150 55 26 69 +68.03 ± 27.48 0 8 30 37 0 +141.71 ± 63.04 ↓

Commit

Commit ID ad2aa8c06f438de8b8bb7b7c8726430e3f2a5685
Author Joost VandeVondele
Date 2022-11-05 08:15:53 UTC
Normalize evaluation Normalizes the internal value as reported by evaluate or search to the UCI centipawn result used in output. This value is derived from the win_rate_model() such that Stockfish outputs an advantage of "100 centipawns" for a position if the engine has a 50% probability to win from this position in selfplay at fishtest LTC time control. The reason to introduce this normalization is that our evaluation is, since NNUE, no longer related to the classical parameter PawnValueEg (=208). This leads to the current evaluation changing quite a bit from release to release, for example, the eval needed to have 50% win probability at fishtest LTC (in cp and internal Value): June 2020 : 113cp (237) June 2021 : 115cp (240) April 2022 : 134cp (279) July 2022 : 167cp (348) With this patch, a 100cp advantage will have a fixed interpretation, i.e. a 50% win chance. To keep this value steady, it will be needed to update the win_rate_model() from time to time, based on fishtest data. This analysis can be performed with a set of scripts currently available at https://github.com/vondele/WLD_model fixes https://github.com/official-stockfish/Stockfish/issues/4155 closes https://github.com/official-stockfish/Stockfish/pull/4216 No functional change
Copyright 2011–2024 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy Desktop Version