Dev Builds » 20230715-0716

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 06:53:02 584028 4000 1379 681 1940 +61.25 ± 5.11 2 185 931 877 5 +125.98 ± 11.14
ncm-dbt-02 06:52:55 587268 4000 1352 686 1962 +58.39 ± 5.09 1 189 961 841 8 +118.92 ± 10.95
ncm-dbt-03 06:53:34 584492 4002 1326 701 1975 +54.71 ± 5.1 0 206 971 817 7 +110.93 ± 10.9
ncm-dbt-04 06:54:09 569427 3998 1362 654 1982 +62.18 ± 4.97 0 162 976 852 9 +126.84 ± 10.83
ncm-dbt-05 06:53:57 577369 4000 1343 679 1978 +58.21 ± 5.01 4 170 990 830 6 +119.5 ± 10.76
20000 6762 3401 9837 +58.95 ± 2.26 7 912 4829 4217 35 +120.4 ± 4.88

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
425984 ncm-dbt-03 584201 2 0 0 2 0.0 ± 34.02 0 0 1 0 0 0.0 ± 30.47
425983 ncm-dbt-04 567918 498 176 93 229 +58.45 ± 14.58 0 25 117 106 1 +118.84 ± 31.55
425982 ncm-dbt-05 575639 500 179 84 237 +66.82 ± 14.2 1 17 119 112 1 +138.99 ± 31.13
425981 ncm-dbt-02 587070 500 171 88 241 +58.21 ± 13.97 0 22 123 105 0 +119.89 ± 30.63
425980 ncm-dbt-01 583908 500 167 88 245 +55.36 ± 14.93 1 26 117 105 1 +113.68 ± 31.56
425979 ncm-dbt-03 583740 500 162 77 261 +59.64 ± 14.59 0 25 116 108 1 +121.46 ± 31.7
425978 ncm-dbt-04 568474 500 172 75 253 +68.27 ± 13.39 0 14 126 109 1 +140.62 ± 29.93
425977 ncm-dbt-05 579826 500 165 70 265 +66.83 ± 14.89 1 23 106 120 0 +140.62 ± 33.22
425976 ncm-dbt-01 583405 500 182 84 234 +68.99 ± 14.0 0 18 117 114 1 +142.26 ± 31.44
425975 ncm-dbt-02 584790 500 181 74 245 +75.52 ± 14.08 0 17 110 122 1 +157.24 ± 32.52
425974 ncm-dbt-03 582360 500 164 93 243 +49.67 ± 14.1 0 25 130 94 1 +99.95 ± 29.7
425973 ncm-dbt-02 588260 500 166 86 248 +56.07 ± 14.43 1 23 121 105 0 +116.78 ± 30.96
425972 ncm-dbt-05 577807 500 166 84 250 +57.5 ± 13.8 0 21 126 103 0 +118.33 ± 30.18
425971 ncm-dbt-04 570348 500 175 89 236 +60.36 ± 13.93 0 19 128 101 2 +121.46 ± 29.83
425970 ncm-dbt-01 584034 500 173 83 244 +63.23 ± 15.79 0 31 101 115 3 +126.18 ± 33.92
425969 ncm-dbt-03 584579 500 162 89 249 +51.09 ± 14.18 0 26 125 99 0 +104.49 ± 30.42
425968 ncm-dbt-03 583531 500 186 76 238 +77.71 ± 14.15 0 18 104 128 0 +164.07 ± 33.53
425967 ncm-dbt-04 569669 500 168 80 252 +61.79 ± 14.27 0 22 119 108 1 +126.18 ± 31.22
425966 ncm-dbt-01 583363 500 163 91 246 +50.38 ± 14.55 0 29 120 101 0 +102.97 ± 31.15
425965 ncm-dbt-02 587070 500 167 80 253 +61.07 ± 13.82 0 19 126 104 1 +124.6 ± 30.12
425964 ncm-dbt-05 577397 500 167 84 249 +58.21 ± 13.55 0 19 129 102 0 +119.89 ± 29.69
425963 ncm-dbt-03 586097 500 169 89 242 +56.07 ± 15.35 0 31 110 107 2 +112.14 ± 32.58
425962 ncm-dbt-04 572034 500 162 68 270 +66.1 ± 14.03 0 17 125 105 3 +132.54 ± 30.2
425961 ncm-dbt-01 584285 500 171 79 250 +64.67 ± 13.97 1 17 121 111 0 +135.76 ± 30.83
425960 ncm-dbt-05 577848 500 172 88 240 +58.93 ± 14.01 0 21 125 103 1 +119.89 ± 30.32
425959 ncm-dbt-02 586731 500 167 90 243 +53.93 ± 14.59 0 25 126 96 3 +106.01 ± 30.26
425958 ncm-dbt-03 585337 500 159 99 242 +41.89 ± 14.34 0 30 131 88 1 +83.57 ± 29.65
425957 ncm-dbt-01 583866 500 182 83 235 +69.71 ± 13.29 0 14 123 113 0 +145.54 ± 30.38
425956 ncm-dbt-05 578753 500 160 92 248 +47.55 ± 14.26 1 24 132 92 1 +96.94 ± 29.43
425955 ncm-dbt-02 588771 500 156 91 253 +45.42 ± 14.81 0 32 122 95 1 +90.97 ± 30.89
425954 ncm-dbt-04 569549 500 169 83 248 +60.36 ± 14.21 0 23 118 109 0 +124.6 ± 31.38
425953 ncm-dbt-01 584285 500 177 88 235 +62.51 ± 14.17 0 22 117 111 0 +129.35 ± 31.52
425952 ncm-dbt-03 585885 500 170 97 233 +51.09 ± 14.18 0 24 131 93 2 +101.46 ± 29.54
425951 ncm-dbt-05 574987 500 170 87 243 +58.21 ± 14.39 0 24 120 105 1 +118.33 ± 31.1
425950 ncm-dbt-04 569071 500 163 79 258 +58.93 ± 14.42 0 24 119 106 1 +119.89 ± 31.25
425949 ncm-dbt-02 588132 500 171 89 240 +57.5 ± 14.63 0 27 114 109 0 +118.33 ± 32.0
425948 ncm-dbt-01 585084 500 164 85 251 +55.36 ± 14.66 0 28 115 107 0 +113.68 ± 31.86
425947 ncm-dbt-03 584706 500 154 81 265 +51.09 ± 14.31 0 27 123 100 0 +104.49 ± 30.71
425946 ncm-dbt-05 576701 500 164 90 246 +51.8 ± 14.21 1 21 133 93 2 +104.49 ± 29.21
425945 ncm-dbt-04 568355 500 177 87 236 +63.23 ± 13.63 0 18 124 108 0 +130.94 ± 30.38
425944 ncm-dbt-02 587325 500 173 88 239 +59.64 ± 14.59 0 24 119 105 2 +119.89 ± 31.25

Commit

Commit ID ee53f8ed2f9418b55b05811da93ddf62f03c255f
Author Linmiao Xu
Date 2023-07-15 07:16:09 UTC
Reintroduce nnue eval pawn count multipliers again With separate multipliers for nnue eval and optimism scaling. This patch used 4 out of 7 params tuned with spsa at 30+0.3 using this tuning config: Value LazyThreshold1 = Value(3622); Value LazyThreshold2 = Value(1962); int psqThresh = 2048; int nnueNpmBase = 945; int nnuePcMult = 0; int optNpmBase = 150; int optPcMult = 0; TUNE(SetRange(3322, 3922), LazyThreshold1); TUNE(SetRange(1662, 2262), LazyThreshold2); TUNE(SetRange(1748, 2348), psqThresh); TUNE(SetRange(745, 1145), nnueNpmBase); TUNE(SetRange(-16, 16), nnuePcMult); TUNE(SetRange(0, 300), optNpmBase); TUNE(SetRange(-16, 16), optPcMult); Passed STC: https://tests.stockfishchess.org/tests/view/64a5a9b402cd07745c60ed07 LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 173632 W: 44417 L: 43903 D: 85312 Ptnml(0-2): 547, 20025, 45068, 20719, 457 Passed LTC: https://tests.stockfishchess.org/tests/view/64a972a302cd07745c6136af LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 277644 W: 70955 L: 70147 D: 136542 Ptnml(0-2): 193, 29902, 77787, 30784, 156 closes https://github.com/official-stockfish/Stockfish/pull/4681 bench 1556301
Copyright 2011–2025 Next Chess Move LLC