Dev Builds » 20240518-1608

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 06:53:44 584085 3998 1489 601 1908 +78.48 ± 4.89 1 104 919 956 19 +162.01 ± 11.14
ncm-dbt-02 06:52:45 586658 4008 1474 650 1884 +72.46 ± 5.0 1 141 906 945 11 +149.76 ± 11.28
ncm-dbt-03 06:53:25 586849 3994 1453 597 1944 +75.64 ± 4.99 2 130 884 972 9 +157.72 ± 11.42
ncm-dbt-04 06:52:29 572031 4000 1483 633 1884 +74.97 ± 5.05 0 139 889 955 17 +154.07 ± 11.39
ncm-dbt-05 06:52:53 584533 4000 1497 603 1900 +78.98 ± 4.88 0 114 887 990 9 +165.15 ± 11.38
20000 7396 3084 9520 +76.1 ± 2.22 4 628 4485 4818 65 +157.7 ± 5.06

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
385220 ncm-dbt-02 585885 8 3 2 3 +43.58 ± 76.58 0 0 3 1 0 +88.62 ± 172.94
385219 ncm-dbt-03 585337 494 175 69 250 +75.73 ± 14.2 0 17 108 121 1 +157.7 ± 32.84
385218 ncm-dbt-01 584369 498 180 75 243 +74.37 ± 13.64 1 10 123 113 2 +154.56 ± 30.22
385217 ncm-dbt-05 584622 500 181 80 239 +71.16 ± 13.79 0 17 115 118 0 +148.85 ± 31.72
385216 ncm-dbt-04 572558 500 182 84 234 +68.99 ± 14.97 0 24 106 118 2 +140.62 ± 33.22
385215 ncm-dbt-02 587877 500 180 76 244 +73.34 ± 14.72 1 19 106 123 1 +153.86 ± 33.21
385214 ncm-dbt-03 586012 500 182 85 233 +68.27 ± 15.08 0 25 105 118 2 +138.99 ± 33.37
385213 ncm-dbt-05 588899 500 184 66 250 +83.57 ± 13.87 0 15 102 133 0 +178.11 ± 33.85
385212 ncm-dbt-01 581693 500 190 74 236 +82.1 ± 13.52 0 13 108 129 0 +174.55 ± 32.75
385211 ncm-dbt-04 571632 500 183 76 241 +75.52 ± 14.08 0 17 110 122 1 +157.24 ± 32.52
385210 ncm-dbt-02 585632 500 193 98 209 +66.82 ± 14.89 0 23 112 112 3 +134.15 ± 32.28
385209 ncm-dbt-03 587197 500 187 84 229 +72.61 ± 14.27 1 15 116 116 2 +150.51 ± 31.54
385208 ncm-dbt-05 582569 500 198 82 220 +82.1 ± 13.52 0 11 114 123 2 +171.02 ± 31.66
385207 ncm-dbt-02 585843 500 171 76 253 +66.82 ± 14.75 0 24 108 117 1 +137.37 ± 32.9
385206 ncm-dbt-01 582611 500 189 72 239 +82.83 ± 13.07 0 9 116 124 1 +174.55 ± 31.22
385205 ncm-dbt-04 569989 500 180 85 235 +66.82 ± 14.62 0 22 113 113 2 +135.76 ± 32.12
385204 ncm-dbt-03 587070 500 181 68 251 +79.9 ± 14.07 0 16 106 127 1 +167.53 ± 33.17
385203 ncm-dbt-02 586943 500 196 89 215 +75.52 ± 13.94 0 17 109 124 0 +158.93 ± 32.69
385202 ncm-dbt-01 585211 500 190 85 225 +74.06 ± 13.89 0 15 117 116 2 +152.18 ± 31.35
385201 ncm-dbt-05 583321 500 179 77 244 +71.88 ± 14.25 0 19 111 119 1 +148.85 ± 32.4
385200 ncm-dbt-04 572114 500 187 65 248 +86.52 ± 13.93 0 12 107 128 3 +179.9 ± 32.89
385199 ncm-dbt-03 585928 500 184 60 256 +88.0 ± 13.03 0 8 111 130 1 +187.16 ± 31.99
385198 ncm-dbt-02 586646 500 193 75 232 +83.57 ± 12.77 0 8 116 126 0 +178.11 ± 31.15
385197 ncm-dbt-01 584748 500 196 71 233 +88.74 ± 13.52 0 8 113 125 4 +183.51 ± 31.65
385196 ncm-dbt-05 582694 500 182 76 242 +74.79 ± 14.06 0 17 111 121 1 +155.54 ± 32.36
385195 ncm-dbt-04 573973 500 185 77 238 +76.25 ± 13.66 0 12 121 114 3 +155.54 ± 30.59
385194 ncm-dbt-03 587325 500 164 79 257 +59.64 ± 13.76 0 19 128 102 1 +121.46 ± 29.83
385193 ncm-dbt-05 583824 500 188 71 241 +82.83 ± 13.54 0 11 113 124 2 +172.78 ± 31.83
385192 ncm-dbt-02 589497 500 186 76 238 +77.7 ± 14.15 0 16 110 122 2 +160.64 ± 32.5
385191 ncm-dbt-01 582068 500 175 75 250 +70.43 ± 14.89 0 21 112 113 4 +140.62 ± 32.26
385190 ncm-dbt-04 571712 500 184 80 236 +73.33 ± 14.15 0 15 120 111 4 +147.19 ± 30.88
385189 ncm-dbt-03 587028 500 189 76 235 +79.9 ± 14.21 1 15 104 130 0 +171.02 ± 33.51
385188 ncm-dbt-02 585928 500 173 84 243 +62.51 ± 13.74 0 18 126 105 1 +127.76 ± 30.09
385187 ncm-dbt-05 586350 500 184 68 248 +82.1 ± 13.98 0 14 108 126 2 +171.02 ± 32.78
385186 ncm-dbt-01 585379 500 184 76 240 +76.25 ± 14.53 0 19 106 123 2 +157.24 ± 33.21
385185 ncm-dbt-04 573123 500 194 89 217 +74.06 ± 13.89 0 16 114 119 1 +153.86 ± 31.85
385184 ncm-dbt-02 585674 500 179 74 247 +74.06 ± 14.18 0 16 116 115 3 +150.51 ± 31.54
385183 ncm-dbt-01 586604 500 185 73 242 +79.17 ± 13.45 0 9 124 113 4 +160.64 ± 29.94
385182 ncm-dbt-03 588899 500 191 76 233 +81.36 ± 13.96 0 15 106 128 1 +171.02 ± 33.15
385181 ncm-dbt-05 583992 500 201 83 216 +83.57 ± 13.25 0 10 113 126 1 +176.33 ± 31.78
385180 ncm-dbt-04 571150 500 188 77 235 +78.43 ± 14.74 0 21 98 130 1 +164.07 ± 34.56

Commit

Commit ID 2694fce928e5eec867d56d853b416c9f389c284d
Author Linmiao Xu
Date 2024-05-18 16:08:39 UTC
Simplify away adjustEval lambda Now that only the shuffling constant differs between nets, a lambda for adjusting eval is no longer needed. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/664806ca6dcff0d1d6b05f34 LLR: 2.99 (-2.94,2.94) <-1.75,0.25> Total: 31552 W: 8175 L: 7959 D: 15418 Ptnml(0-2): 76, 3180, 9065, 3362, 93 closes https://github.com/official-stockfish/Stockfish/pull/5260 No functional change
Copyright 2011–2024 Next Chess Move LLC