Dev Builds » 20230102-1810

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 05:00:31 1113965 1658 654 159 845 +106.99 ± 7.8 0 31 291 488 19 +227.13 ± 19.98
ncm-dbt-02 04:58:26 1230805 1658 680 190 788 +105.84 ± 7.72 0 32 290 492 15 +226.51 ± 20.02
ncm-dbt-03 05:01:08 1230792 1684 673 196 815 +101.18 ± 7.8 0 40 299 489 14 +214.79 ± 19.73
ncm-dbt-04 04:59:37 1232995 1680 679 167 834 +109.36 ± 7.42 0 26 288 514 12 +238.25 ± 20.07
ncm-dbt-05 04:58:23 1239113 1654 672 165 817 +110.04 ± 7.61 0 28 278 507 14 +238.73 ± 20.45
ncm-dbt-06 05:00:37 1235033 1666 689 176 801 +110.57 ± 7.6 1 25 282 510 15 +240.3 ± 20.29
ncm-et-3 06:23:51 1298554 1664 675 178 811 +107.03 ± 7.81 0 24 314 467 27 +222.36 ± 19.14
ncm-et-4 06:23:47 1304171 1668 668 182 818 +104.25 ± 7.87 1 33 297 485 18 +221.06 ± 19.78
ncm-et-9 06:22:57 1295504 1658 669 172 817 +107.45 ± 8.01 0 36 282 489 22 +226.51 ± 20.32
ncm-et-10 06:23:47 1296655 1676 686 183 807 +107.58 ± 7.41 0 22 306 495 15 +231.39 ± 19.4
ncm-et-13 06:23:29 1302661 1670 658 171 841 +104.35 ± 7.84 0 36 293 489 17 +221.33 ± 19.93
ncm-et-15 06:23:20 1298679 1664 657 166 841 +105.66 ± 7.76 0 35 285 498 14 +226.68 ± 20.21
20000 8060 2105 9835 +106.68 ± 2.23 2 368 3505 5923 202 +227.82 ± 5.75

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
189889 ncm-dbt-05 1237287 154 67 17 70 +117.03 ± 26.0 0 3 23 49 2 +253.8 ± 73.27
189888 ncm-dbt-02 1226743 158 66 19 73 +106.57 ± 23.71 0 3 26 50 0 +238.09 ± 68.56
189887 ncm-dbt-01 1119972 158 62 12 84 +113.85 ± 26.46 0 4 23 50 2 +244.98 ± 72.99
189886 ncm-dbt-06 1233783 166 61 22 83 +83.18 ± 24.87 0 6 32 45 0 +177.16 ± 61.23
189885 ncm-dbt-04 1239043 180 61 21 98 +78.52 ± 21.91 0 4 42 44 0 +165.99 ± 52.46
189884 ncm-dbt-03 1239753 184 77 21 86 +109.2 ± 25.17 0 5 29 55 3 +228.12 ± 64.58
189883 ncm-dbt-01 1119009 500 202 46 252 +112.14 ± 14.22 0 7 88 147 8 +236.51 ± 36.44
189882 ncm-dbt-05 1249449 500 201 64 235 +97.69 ± 14.13 0 12 92 143 3 +207.95 ± 35.71
189881 ncm-dbt-06 1256218 500 207 41 252 +119.89 ± 14.35 1 5 79 157 8 +261.07 ± 38.58
189880 ncm-dbt-02 1235531 500 198 66 236 +93.95 ± 13.92 0 9 105 131 5 +194.57 ± 33.11
189879 ncm-dbt-04 1241389 500 201 48 251 +109.83 ± 13.56 0 8 84 155 3 +240.82 ± 37.4
189878 ncm-dbt-03 1222332 500 199 56 245 +102.22 ± 15.08 0 14 86 143 7 +211.87 ± 36.97
189877 ncm-dbt-05 1239111 500 197 42 261 +111.37 ± 13.39 0 5 90 150 5 +240.82 ± 35.87
189876 ncm-dbt-06 1230155 500 206 51 243 +111.37 ± 13.39 0 9 78 162 1 +249.64 ± 38.9
189875 ncm-dbt-01 1110248 500 197 57 246 +99.95 ± 14.46 0 11 94 139 6 +207.95 ± 35.29
189874 ncm-dbt-04 1224228 500 205 49 246 +112.14 ± 13.39 0 6 86 154 4 +245.2 ± 36.85
189873 ncm-dbt-02 1236150 500 207 59 234 +106.01 ± 14.2 0 10 87 148 5 +226.0 ± 36.75
189872 ncm-dbt-03 1237074 500 193 55 252 +98.44 ± 13.82 0 11 92 145 2 +211.87 ± 35.7
189871 ncm-dbt-04 1227322 500 212 49 239 +117.55 ± 13.87 0 8 76 161 5 +258.75 ± 39.42
189870 ncm-dbt-02 1224798 500 209 46 245 +117.55 ± 14.2 0 10 72 163 5 +258.75 ± 40.49
189869 ncm-dbt-05 1230606 500 207 42 251 +119.11 ± 13.69 0 8 73 165 4 +265.78 ± 40.25
189868 ncm-dbt-06 1219976 500 215 62 223 +109.83 ± 13.56 0 5 93 146 6 +234.38 ± 35.22
189867 ncm-dbt-01 1106634 500 193 44 263 +106.77 ± 13.72 0 9 86 152 3 +232.26 ± 36.96
189866 ncm-dbt-03 1224010 500 204 64 232 +99.95 ± 13.68 0 10 92 146 2 +215.85 ± 35.68
166838 ncm-et-9 1298332 158 63 13 82 +113.85 ± 21.65 0 1 27 51 0 +259.28 ± 66.64
166837 ncm-et-3 1308466 164 65 20 79 +97.83 ± 23.07 0 1 37 42 2 +202.34 ± 55.11
166836 ncm-et-13 1305201 170 65 17 88 +100.83 ± 24.24 0 3 33 47 2 +210.48 ± 60.09
166835 ncm-et-15 1312512 164 60 17 87 +93.27 ± 22.97 0 3 33 46 0 +202.34 ± 59.98
166834 ncm-et-4 1309293 168 73 21 74 +111.19 ± 27.64 1 3 26 51 3 +238.25 ± 68.51
166833 ncm-et-10 1307252 176 72 18 86 +110.14 ± 23.78 0 3 30 53 2 +235.93 ± 63.51
166832 ncm-et-9 1287227 500 197 51 252 +104.49 ± 15.25 0 15 81 147 7 +217.85 ± 38.05
166831 ncm-et-3 1301519 500 200 57 243 +102.22 ± 15.08 0 11 95 134 10 +206.01 ± 35.09
166830 ncm-et-15 1298803 500 199 54 247 +103.73 ± 14.8 0 15 79 152 4 +221.9 ± 38.51
166829 ncm-et-13 1301336 500 197 57 246 +99.95 ± 14.76 0 13 90 141 6 +207.95 ± 36.13
166828 ncm-et-4 1303946 500 200 64 236 +96.94 ± 13.96 0 11 95 141 3 +206.01 ± 35.09
166827 ncm-et-10 1298151 500 208 58 234 +107.54 ± 13.23 0 5 94 147 4 +232.26 ± 35.0
166826 ncm-et-9 1297060 500 208 54 238 +110.6 ± 14.84 0 11 82 149 8 +232.26 ± 37.9
166825 ncm-et-15 1286803 500 200 43 257 +112.91 ± 13.56 0 6 86 153 5 +245.2 ± 36.85
166824 ncm-et-3 1306429 500 213 51 236 +116.77 ± 14.53 0 9 78 155 8 +249.64 ± 38.9
166823 ncm-et-13 1302885 500 203 45 252 +113.68 ± 13.89 0 7 84 153 6 +245.2 ± 37.37
166822 ncm-et-4 1302492 500 197 41 262 +112.14 ± 13.56 0 3 96 143 8 +236.51 ± 34.4
166821 ncm-et-10 1287704 500 198 51 251 +105.25 ± 13.39 0 7 92 148 3 +228.08 ± 35.56
166820 ncm-et-9 1299399 500 201 54 245 +105.25 ± 14.35 0 9 92 142 7 +219.87 ± 35.65
166819 ncm-et-15 1296600 500 198 52 250 +104.49 ± 14.35 0 11 87 147 5 +221.9 ± 36.76
166818 ncm-et-13 1301224 500 193 52 255 +100.7 ± 14.32 0 13 86 148 3 +215.85 ± 36.98
166817 ncm-et-3 1277805 500 197 50 253 +105.25 ± 13.39 0 3 104 136 7 +219.87 ± 32.82
166816 ncm-et-4 1300954 500 198 56 246 +101.46 ± 14.93 0 16 80 150 4 +215.85 ± 38.24
166815 ncm-et-10 1293513 500 208 56 236 +109.07 ± 13.89 0 7 90 147 6 +232.26 ± 35.99

Commit

Commit ID a6fa683418c6a74491035601e16497851eea6be6
Author Linmiao Xu
Date 2023-01-02 18:10:14 UTC
Update default net to nn-a3dc078bafc7.nnue This is a later epoch (epoch 859) from the same experiment run that trained yesterday's master net nn-60fa44e376d9.nnue (epoch 779). The experiment was manually paused around epoch 790 and unpaused with max epoch increased to 900 mainly to get more local elo data without letting the GPU idle. nn-60fa44e376d9.nnue is from #4314 nn-335a9b2d8a80.nnue is from #4295 Local elo vs. nn-335a9b2d8a80.nnue at 25k nodes per move: experiment_leela93-dfrc99-filt-only-T80-oct-nov-skip28 run_0/nn-epoch779.nnue (nn-60fa44e376d9.nnue) : 5.0 +/- 1.2 run_0/nn-epoch859.nnue (nn-a3dc078bafc7.nnue) : 5.6 +/- 1.6 Passed STC vs. nn-335a9b2d8a80.nnue https://tests.stockfishchess.org/tests/view/63ae10495bd1e5f27f13d94f LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 37536 W: 10088 L: 9781 D: 17667 Ptnml(0-2): 110, 4006, 10223, 4325, 104 An LTC test vs. nn-335a9b2d8a80.nnue was paused due to nn-60fa44e376d9.nnue passing LTC first: https://tests.stockfishchess.org/tests/view/63ae5d34331d5fca5113703b Passed LTC vs. nn-60fa44e376d9.nnue https://tests.stockfishchess.org/tests/view/63af1e41465d2b022dbce4e7 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 148704 W: 39672 L: 39155 D: 69877 Ptnml(0-2): 59, 14443, 44843, 14936, 71 closes https://github.com/official-stockfish/Stockfish/pull/4319 bench 3984365
Copyright 2011–2024 Next Chess Move LLC