Dev Builds » 20251112-0949

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 06:09:46 582739 3650 1515 412 1723 +108.38 ± 4.98 1 53 633 1118 20 +237.57 ± 13.51
ncm-dbt-02 06:10:03 586152 3642 1549 378 1715 +115.82 ± 4.94 0 38 608 1141 34 +254.38 ± 13.76
ncm-dbt-03 06:10:01 585867 3636 1547 417 1672 +111.67 ± 4.9 0 46 615 1138 19 +246.92 ± 13.7
ncm-dbt-04 06:09:51 567028 3654 1506 408 1740 +107.73 ± 5.01 1 57 632 1117 20 +235.76 ± 13.53
ncm-dbt-05 06:10:16 583653 3624 1520 382 1722 +112.92 ± 4.91 0 47 599 1147 19 +250.51 ± 13.89
18206 7637 1997 8572 +111.29 ± 2.21 2 241 3087 5661 112 +244.92 ± 6.11

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
441882 ncm-dbt-05 581652 124 46 8 70 +110.0 ± 26.28 0 1 23 37 1 +239.08 ± 72.27
441881 ncm-dbt-03 586139 136 57 16 63 +108.09 ± 29.38 0 5 18 44 1 +234.51 ± 81.77
441880 ncm-dbt-02 585253 142 57 12 73 +114.02 ± 21.68 0 0 26 45 0 +259.78 ± 66.85
441879 ncm-dbt-01 584664 150 60 14 76 +110.09 ± 22.33 0 1 27 47 0 +248.15 ± 66.43
441878 ncm-dbt-04 567403 154 57 23 74 +77.98 ± 29.1 0 9 26 41 1 +159.18 ± 67.04
441877 ncm-dbt-03 586816 500 214 55 231 +114.45 ± 13.03 0 6 81 161 2 +256.44 ± 38.07
441876 ncm-dbt-05 582277 500 214 47 239 +120.67 ± 13.5 0 7 73 166 4 +270.57 ± 40.25
441875 ncm-dbt-02 586858 500 212 53 235 +114.45 ± 13.89 0 6 86 151 7 +245.2 ± 36.85
441874 ncm-dbt-01 577684 500 218 61 221 +112.91 ± 13.39 0 7 82 158 3 +249.64 ± 37.86
441873 ncm-dbt-04 567720 500 206 61 233 +103.73 ± 13.55 0 8 92 147 3 +223.94 ± 35.61
441872 ncm-dbt-03 585042 500 207 67 226 +99.95 ± 14.0 0 13 85 151 1 +217.85 ± 37.2
441871 ncm-dbt-05 580116 500 217 47 236 +123.02 ± 12.74 0 6 69 174 1 +285.49 ± 41.44
441870 ncm-dbt-02 583656 500 222 48 230 +126.17 ± 13.6 0 7 67 171 5 +285.49 ± 42.08
441869 ncm-dbt-01 582569 500 207 60 233 +105.25 ± 13.22 0 7 91 150 2 +230.16 ± 35.78
441868 ncm-dbt-04 566928 500 219 59 222 +115.22 ± 13.38 0 7 79 161 3 +256.44 ± 38.62
441867 ncm-dbt-03 588174 500 217 62 221 +111.37 ± 12.87 0 5 87 156 2 +247.41 ± 36.56
441866 ncm-dbt-05 577561 500 211 50 239 +116.0 ± 12.47 0 3 85 160 2 +261.07 ± 36.86
441865 ncm-dbt-02 587325 500 211 61 228 +107.54 ± 13.06 0 5 93 149 3 +234.38 ± 35.22
441864 ncm-dbt-01 584369 500 202 65 233 +97.69 ± 12.67 0 6 101 143 0 +213.85 ± 33.67
441863 ncm-dbt-04 566138 500 208 61 231 +105.25 ± 12.71 0 4 97 147 2 +230.16 ± 34.29
441862 ncm-dbt-03 587282 500 208 60 232 +106.01 ± 12.71 0 4 96 148 2 +232.26 ± 34.5
441861 ncm-dbt-05 584832 500 207 59 234 +106.01 ± 13.56 0 7 92 147 4 +228.08 ± 35.56
441860 ncm-dbt-04 567205 500 205 43 252 +116.78 ± 14.21 1 10 67 170 2 +265.78 ± 41.9
441859 ncm-dbt-02 585379 500 214 58 228 +112.14 ± 12.69 0 4 88 156 2 +249.64 ± 36.24
441858 ncm-dbt-01 581236 500 197 52 251 +103.73 ± 14.5 1 10 86 149 4 +223.94 ± 36.98
441857 ncm-dbt-03 584495 500 208 58 234 +107.54 ± 12.53 0 4 93 152 1 +238.66 ± 35.13
441856 ncm-dbt-05 579744 500 220 57 223 +117.55 ± 13.53 0 5 83 156 6 +256.44 ± 37.51
441855 ncm-dbt-04 568673 500 210 58 232 +109.07 ± 13.73 0 8 86 152 4 +236.51 ± 36.93
441854 ncm-dbt-01 582652 500 208 58 234 +107.54 ± 13.73 0 10 82 156 2 +236.51 ± 37.9
441853 ncm-dbt-02 587452 500 218 60 222 +113.68 ± 14.22 0 8 83 152 7 +243.0 ± 37.64
441852 ncm-dbt-05 584832 500 195 57 248 +98.44 ± 13.34 0 10 92 148 0 +215.85 ± 35.68
441851 ncm-dbt-03 584034 500 225 48 227 +128.55 ± 13.01 0 2 76 165 7 +288.06 ± 39.11
441850 ncm-dbt-01 583405 500 214 52 234 +116.77 ± 13.88 0 6 83 154 7 +251.89 ± 37.57
441849 ncm-dbt-04 567126 500 201 54 245 +105.25 ± 12.35 0 3 98 148 1 +232.26 ± 33.99
441848 ncm-dbt-02 587113 500 202 38 260 +118.33 ± 12.44 0 1 88 157 4 +263.42 ± 35.9
441847 ncm-dbt-01 585337 500 209 50 241 +114.45 ± 13.03 0 6 81 161 2 +256.44 ± 38.07
441846 ncm-dbt-04 565037 500 200 49 251 +108.3 ± 13.73 0 8 87 151 4 +234.38 ± 36.71
441845 ncm-dbt-03 584958 500 211 51 238 +115.22 ± 13.38 0 7 79 161 3 +256.44 ± 38.62
441844 ncm-dbt-02 586181 500 213 48 239 +119.11 ± 13.86 0 7 77 160 6 +261.07 ± 39.14
441843 ncm-dbt-05 598215 500 210 57 233 +109.83 ± 13.23 0 8 82 159 1 +245.2 ± 37.88

Commit

Commit ID 8e5392d79a36aba5b997cf6fb590937e3e624e80
Author sscg13
Date 2025-11-12 09:49:39 UTC
Update NNUE architecture to SFNNv10 with Threat Inputs and net nn-49c1193b131c.nnue This commit introduces Full Threat Input features, which are a subset of Piece(Square)-Piece(Square) pairs. In any given position, the active features consist of pairs where the second piece’s square lies in the attack set of the first piece. This is an extremely simplified explanation that leaves out many details. The already-used HalfKAv2_hm feature set completes the input features. Minor quantization changes have also been made. The net nn-49c1193b131c.nnue was trained by vondele using the following setup: https://github.com/vondele/nettest/blob/7de71238e9b295e3f88ed7c9c5936af632c9b981/threats.yaml A graphical version of an earlier scheme (with less refinement) that illustrates the core concepts can be found attached. [NewInputs.pdf](https://github.com/user-attachments/files/23478441/NewInputs.pdf) Further information, as well as a brief description of the history of development, can be found attached. [Stockfish threat inputs PR summary.pdf](https://github.com/user-attachments/files/23478634/Stockfish.threat.inputs.PR.summary.pdf) This has been a huge effort spanning over half a year, with the original [discussion thread](https://discord.com/channels/435943710472011776/1336647760388034610) reaching over 11k messages. Thanks to everyone who has contributed. Monty PRs: https://github.com/official-monty/Monty/pull/87 (Initial threat input PR) https://github.com/official-monty/Monty/pull/114 (Fixed threat indexing to take into account colour correctly) https://github.com/official-monty/Monty/pull/116 (i8 quantisation of weights whilst keeping calculations in i16) Yukari commit: https://github.com/yukarichess/yukari/commit/2d482c64a79cec03cf4987d5289334b9cdc737bc (Threat inputs merged) Plentychess PRs: https://github.com/Yoshie2000/PlentyChess/pull/400 (Threat inputs merged) https://github.com/Yoshie2000/PlentyChess/pull/411 (Threat input weights quantised to i8) Passed STC: LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 63424 W: 16956 L: 16591 D: 29877 Ptnml(0-2): 276, 7522, 15797, 7795, 322 https://tests.stockfishchess.org/tests/view/69105b3dec1d00d2c195c569 Passed LTC: LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 27876 W: 7417 L: 7110 D: 13349 Ptnml(0-2): 23, 3033, 7530, 3318, 34 https://tests.stockfishchess.org/tests/view/6910d817ec1d00d2c195c66e Passed VVLTC (Hash accidentally set to 1/2 normal value for both sides): LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 12458 W: 3353 L: 3102 D: 6003 Ptnml(0-2): 0, 1106, 3767, 1355, 1 https://tests.stockfishchess.org/tests/view/69115a26ec1d00d2c195c7cd This version has also passed non-regression LTC against the originally passed version: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 51144 W: 13086 L: 12903 D: 25155 Ptnml(0-2): 22, 5167, 15018, 5336, 29 https://tests.stockfishchess.org/tests/view/69138a317ca87818523314bf LTC elo estimate on ARM: 1 patch : 13.9 1.9 38296.5 73728 52 2 master : 0.0 ---- 35431.5 73728 48 closes https://github.com/official-stockfish/Stockfish/pull/6411 bench: 2626086 Co-authored-by: Shawn Xu <xu107288696@gmail.com> Co-authored-by: Timothy Herchen <timothy.herchen@gmail.com> Co-authored-by: Viren6 <94880762+Viren6@users.noreply.github.com> Co-authored-by: Yoshie2000 <patrick.leonhardt@gmx.net> Co-authored-by: Joost Vandevondele <Joost.VandeVondele@gmail.com> Co-authored-by: rn5f107s2 <clemens.lerchl@gmail.com> Co-authored-by: cj5716 <125858804+cj5716@users.noreply.github.com> Co-authored-by: AliceRoselia <63040919+AliceRoselia@users.noreply.github.com> Co-authored-by: Linmiao Xu <linmiao.xu@gmail.com> Co-authored-by: Disservin <disservin.social@gmail.com>
Copyright 2011–2025 Next Chess Move LLC