Dev Builds » 20200829-1956

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 06:28:00 580956 4002 135 1945 1922 -169.39 ± 4.41 116 1588 287 10 0 -432.19 ± 20.17
ncm-dbt-02 06:28:36 586824 4000 167 1995 1838 -171.46 ± 4.39 118 1603 268 11 0 -442.79 ± 20.88
ncm-dbt-03 06:25:19 585431 4000 147 1990 1863 -173.11 ± 4.39 126 1599 267 8 0 -447.36 ± 20.92
ncm-dbt-04 06:28:02 567154 4000 155 2007 1838 -174.11 ± 4.34 124 1612 256 8 0 -454.76 ± 21.37
ncm-dbt-05 06:31:25 582934 3998 164 2009 1825 -173.44 ± 4.43 129 1596 265 9 0 -447.27 ± 21.0
20000 768 9946 9286 -172.3 ± 1.96 613 7998 1343 46 0 -444.74 ± 9.3

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
443872 ncm-dbt-01 579661 2 0 1 1 -189.7 ± 55.98 0 1 0 0 0 -1129.65 ± 376.02
443871 ncm-dbt-05 582861 498 32 257 209 -169.19 ± 14.15 22 182 44 1 0 -396.95 ± 52.42
443870 ncm-dbt-02 587197 500 18 254 228 -178.11 ± 12.3 17 203 29 1 0 -471.92 ± 65.71
443869 ncm-dbt-03 585253 500 19 250 231 -173.66 ± 11.44 13 205 32 0 0 -466.03 ± 62.14
443868 ncm-dbt-04 568593 500 24 249 227 -168.4 ± 13.51 19 188 42 1 0 -406.2 ± 53.75
443867 ncm-dbt-01 582945 500 17 254 229 -179.0 ± 13.19 19 202 26 3 0 -466.04 ± 69.04
443866 ncm-dbt-05 585970 500 21 252 227 -173.66 ± 12.92 17 199 32 2 0 -444.09 ± 62.18
443865 ncm-dbt-02 588643 500 25 237 238 -157.23 ± 12.9 11 193 43 3 0 -385.59 ± 53.09
443864 ncm-dbt-04 564644 500 18 259 223 -182.6 ± 12.89 20 203 25 2 0 -484.25 ± 70.99
443863 ncm-dbt-03 585379 500 12 243 245 -173.66 ± 12.68 18 195 37 0 0 -438.94 ± 57.41
443862 ncm-dbt-01 576660 500 16 247 237 -173.66 ± 12.68 17 198 34 1 0 -444.09 ± 60.25
443861 ncm-dbt-03 587792 500 17 253 230 -178.11 ± 12.79 18 202 28 2 0 -466.04 ± 66.79
443860 ncm-dbt-05 584034 500 22 248 230 -169.27 ± 11.32 11 204 35 0 0 -449.34 ± 59.17
443859 ncm-dbt-04 566533 500 18 243 239 -168.4 ± 11.9 13 199 38 0 0 -433.93 ± 56.58
443858 ncm-dbt-01 580240 500 22 253 225 -173.66 ± 12.92 18 196 35 1 0 -438.95 ± 59.31
443857 ncm-dbt-02 588302 500 17 248 235 -173.66 ± 12.68 17 198 34 1 0 -444.09 ± 60.25
443856 ncm-dbt-01 582611 500 14 232 254 -162.35 ± 12.36 11 198 39 2 0 -410.58 ± 55.96
443855 ncm-dbt-05 585042 500 17 248 235 -173.66 ± 12.92 18 196 35 1 0 -438.95 ± 59.31
443854 ncm-dbt-03 586266 500 26 237 237 -156.39 ± 11.83 7 199 42 2 0 -397.72 ± 53.79
443853 ncm-dbt-02 585590 500 23 248 229 -168.4 ± 11.65 12 201 37 0 0 -438.94 ± 57.41
443852 ncm-dbt-04 566454 500 16 258 226 -183.51 ± 12.04 18 207 24 1 0 -504.32 ± 72.94
443851 ncm-dbt-01 581277 500 11 229 260 -162.35 ± 11.4 9 200 41 0 0 -419.6 ± 54.3
443850 ncm-dbt-03 582945 500 19 258 223 -180.8 ± 13.28 22 196 31 1 0 -460.32 ± 63.35
443849 ncm-dbt-02 587919 500 24 250 226 -169.27 ± 13.67 17 196 33 4 0 -419.61 ± 60.67
443848 ncm-dbt-05 580489 500 19 251 230 -174.55 ± 11.08 12 208 30 0 0 -477.98 ± 64.39
443847 ncm-dbt-04 565981 500 20 252 228 -174.55 ± 11.87 15 202 33 0 0 -460.31 ± 61.1
443286 ncm-dbt-01 580530 500 25 241 234 -160.64 ± 12.69 12 194 42 2 0 -397.72 ± 53.79
443285 ncm-dbt-05 581985 500 14 254 232 -181.7 ± 11.69 15 212 21 2 0 -511.5 ± 78.03
443284 ncm-dbt-02 586520 500 21 258 221 -179.0 ± 11.96 17 203 30 0 0 -477.98 ± 64.39
443283 ncm-dbt-04 567205 500 21 250 229 -171.9 ± 11.85 13 204 32 1 0 -454.76 ± 62.27
443282 ncm-dbt-03 586901 500 18 253 229 -177.21 ± 13.34 21 194 34 1 0 -444.09 ± 60.25
443281 ncm-dbt-05 581277 500 19 253 228 -176.32 ± 12.7 17 202 29 2 0 -460.32 ± 65.55
443280 ncm-dbt-01 581569 500 16 249 235 -175.43 ± 12.54 17 200 32 1 0 -454.76 ± 62.27
443279 ncm-dbt-02 586604 500 20 245 235 -168.4 ± 11.14 9 208 32 1 0 -454.76 ± 62.27
443278 ncm-dbt-03 582694 500 16 246 238 -172.78 ± 11.26 11 209 29 1 0 -471.92 ± 65.71
443277 ncm-dbt-04 568156 500 16 256 228 -181.7 ± 12.72 18 207 22 3 0 -490.71 ± 75.32
443276 ncm-dbt-01 583112 500 14 239 247 -168.4 ± 11.9 13 199 38 0 0 -433.93 ± 56.58
443275 ncm-dbt-05 581818 500 20 246 234 -169.27 ± 13.01 17 193 39 1 0 -419.61 ± 55.94
443274 ncm-dbt-03 586223 500 20 250 230 -172.78 ± 12.51 16 199 34 1 0 -444.09 ± 60.25
443273 ncm-dbt-02 583824 500 19 255 226 -178.11 ± 12.55 18 201 30 1 0 -466.04 ± 64.5
443272 ncm-dbt-04 569669 500 22 240 238 -162.35 ± 11.15 8 202 40 0 0 -424.27 ± 55.03

Commit

Commit ID 406979ea12ee7828e079871b0f9f3dc8f127a741
Author Stéphane Nicolet
Date 2020-08-29 19:56:00 UTC
Embed default net, and simplify using non-default nets covers the most important cases from the user perspective: It embeds the default net in the binary, so a download of that binary will result in a working engine with the default net. The engine will be functional in the default mode without any additional user action. It allows non-default nets to be used, which will be looked for in up to three directories (working directory, location of the binary, and optionally a specific default directory). This mechanism is also kept for those developers that use MSVC, the one compiler that doesn't have an easy mechanism for embedding data. It is possible to disable embedding, and instead specify a specific directory, e.g. linux distros might want to use CXXFLAGS="-DNNUE_EMBEDDING_OFF -DDEFAULT_NNUE_DIRECTORY=/usr/share/games/stockfish/" make -j ARCH=x86-64 profile-build passed STC non-regression: https://tests.stockfishchess.org/tests/view/5f4a581c150f0aef5f8ae03a LLR: 2.95 (-2.94,2.94) {-1.25,-0.25} Total: 66928 W: 7202 L: 7147 D: 52579 Ptnml(0-2): 291, 5309, 22211, 5360, 293 closes https://github.com/official-stockfish/Stockfish/pull/3070 fixes https://github.com/official-stockfish/Stockfish/issues/3030 No functional change.
Copyright 2011–2025 Next Chess Move LLC