Dev Builds » 20240706-1543

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 06:53:30 584040 4002 1489 596 1917 +78.85 ± 5.0 2 125 863 1000 11 +164.84 ± 11.57
ncm-dbt-02 06:53:16 587766 4016 1490 583 1943 +79.84 ± 4.88 0 112 889 995 12 +166.54 ± 11.36
ncm-dbt-03 06:52:53 587524 4000 1474 601 1925 +77.07 ± 4.95 0 128 881 981 10 +160.42 ± 11.44
ncm-dbt-04 06:51:01 571046 4000 1506 626 1868 +77.71 ± 4.92 3 112 898 976 11 +162.35 ± 11.3
ncm-dbt-05 06:53:16 586258 3982 1476 597 1909 +77.98 ± 5.02 2 129 858 992 10 +162.98 ± 11.61
20000 7435 3003 9562 +78.29 ± 2.22 7 606 4389 4944 54 +163.42 ± 5.12

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
391272 ncm-dbt-01 582819 2 1 1 0 0.0 ± 34.02 0 0 1 0 0 0.0 ± 30.47 ↓
391271 ncm-dbt-02 587197 16 7 1 8 +136.89 ± 61.78 0 0 2 6 0 +337.87 ± 515.83 ↓
391270 ncm-dbt-05 584327 482 168 75 239 +67.89 ± 14.77 0 19 113 106 3 +136.34 ± 32.03 ↓
391269 ncm-dbt-03 586858 500 192 80 228 +79.17 ± 14.34 0 16 109 122 3 +162.35 ± 32.67 ↓
391268 ncm-dbt-04 569949 500 198 74 228 +88.0 ± 13.66 1 9 106 133 1 +189.0 ± 32.98 ↓
391267 ncm-dbt-02 587028 500 192 80 228 +79.17 ± 13.29 0 11 117 121 1 +165.8 ± 31.17 ↓
391266 ncm-dbt-01 585506 500 187 69 244 +83.57 ± 14.01 0 14 106 128 2 +174.55 ± 33.13 ↓
391265 ncm-dbt-05 581985 500 190 77 233 +79.9 ± 14.5 1 15 106 126 2 +167.53 ± 33.17 ↓
391264 ncm-dbt-03 587537 500 190 73 237 +82.83 ± 13.7 0 12 111 125 2 +172.78 ± 32.21 ↓
391263 ncm-dbt-04 571190 500 193 75 232 +83.57 ± 13.71 0 11 113 123 3 +172.78 ± 31.83 ↓
391262 ncm-dbt-02 588430 500 188 73 239 +81.36 ± 13.81 0 13 111 124 2 +169.27 ± 32.25 ↓
391261 ncm-dbt-01 583196 500 188 75 237 +79.9 ± 14.07 0 17 103 130 0 +169.27 ± 33.7 ↓
391260 ncm-dbt-05 586604 500 175 82 243 +65.39 ± 14.56 1 21 112 116 0 +137.37 ± 32.27 ↓
391259 ncm-dbt-03 587664 500 181 75 244 +74.79 ± 13.76 0 15 115 119 1 +155.54 ± 31.67 ↓
391258 ncm-dbt-04 569629 500 181 78 241 +72.61 ± 13.54 1 11 123 114 1 +152.18 ± 30.28 ↓
391257 ncm-dbt-01 582444 500 188 78 234 +77.71 ± 14.15 1 13 113 121 2 +162.35 ± 31.95 ↓
391256 ncm-dbt-02 589069 500 182 86 232 +67.54 ± 13.95 0 18 119 112 1 +138.99 ± 31.13 ↓
391255 ncm-dbt-05 583614 500 189 56 255 +94.69 ± 13.78 0 11 97 140 2 +202.15 ± 34.7 ↓
391254 ncm-dbt-03 588813 500 174 85 241 +62.51 ± 14.72 0 26 109 115 0 +129.35 ± 32.75 ↓
391253 ncm-dbt-04 571833 500 189 79 232 +77.71 ± 14.15 1 13 113 121 2 +162.35 ± 31.95 ↓
391252 ncm-dbt-01 583740 500 192 68 240 +88.0 ± 14.12 0 14 100 134 2 +185.33 ± 34.19 ↓
391251 ncm-dbt-02 585674 500 182 61 257 +85.78 ± 13.92 0 12 108 127 3 +178.11 ± 32.72 ↓
391250 ncm-dbt-05 585084 500 178 67 255 +78.44 ± 14.02 0 17 105 128 0 +165.8 ± 33.35 ↓
391249 ncm-dbt-03 587197 500 185 69 246 +82.1 ± 13.98 0 16 102 132 0 +174.55 ± 33.86 ↓
391248 ncm-dbt-04 570709 500 171 77 252 +66.1 ± 13.6 0 16 125 108 1 +135.76 ± 30.17 ↓
391247 ncm-dbt-01 584076 500 181 80 239 +71.16 ± 13.49 0 15 119 116 0 +148.85 ± 31.04 ↓
391246 ncm-dbt-02 590310 500 186 74 240 +79.17 ± 14.62 0 19 102 127 2 +164.07 ± 33.88 ↓
391245 ncm-dbt-05 581028 500 182 87 231 +66.82 ± 14.48 0 23 109 118 0 +138.99 ± 32.74 ↓
391244 ncm-dbt-04 571150 500 198 85 217 +79.9 ± 14.36 0 16 108 123 3 +164.07 ± 32.83 ↓
391243 ncm-dbt-03 586985 500 184 84 232 +70.44 ± 13.47 0 15 120 115 0 +147.19 ± 30.88 ↓
391242 ncm-dbt-01 586054 500 185 75 240 +77.7 ± 14.44 0 19 103 127 1 +162.35 ± 33.71 ↓
391241 ncm-dbt-02 586689 500 180 72 248 +76.25 ± 13.66 0 15 112 123 0 +160.64 ± 32.15 ↓
391240 ncm-dbt-04 571029 500 186 82 232 +73.34 ± 13.57 0 15 116 119 0 +153.86 ± 31.51 ↓
391239 ncm-dbt-05 588771 500 202 81 217 +85.78 ± 13.92 0 14 102 133 1 +181.7 ± 33.83 ↓
391238 ncm-dbt-03 584706 500 182 73 245 +76.97 ± 14.56 0 19 105 124 2 +158.93 ± 33.37 ↓
391237 ncm-dbt-01 583614 500 180 72 248 +76.25 ± 14.67 1 17 107 123 2 +158.93 ± 33.03 ↓
391236 ncm-dbt-02 586774 500 187 65 248 +86.52 ± 13.32 0 10 109 130 1 +183.51 ± 32.46 ↓
391235 ncm-dbt-04 572880 500 190 76 234 +80.63 ± 14.66 0 21 94 135 0 +171.02 ± 35.27 ↓
391234 ncm-dbt-05 598656 500 192 72 236 +85.04 ± 13.28 0 9 114 125 2 +178.11 ± 31.55 ↓
391233 ncm-dbt-02 588728 500 186 71 243 +81.36 ± 13.96 0 14 109 125 2 +169.27 ± 32.62 ↓
391232 ncm-dbt-03 590438 500 186 62 252 +88.0 ± 13.35 0 9 110 129 2 +185.33 ± 32.23 ↓
391231 ncm-dbt-01 584916 500 187 78 235 +76.97 ± 14.13 0 16 111 121 2 +158.93 ± 32.34 ↓

Commit

Commit ID d212e663bb00226f861f3046b36a5d8a3a127865
Author Stéphane Nicolet
Date 2024-07-06 15:43:39 UTC
Introduction evaluation grain of 16 (and randomize) This patch uses an evaluation grain of 16 in order to get more cutoffs in the alpha-beta algorithm. For a discussion of the efficiency of alpha-beta related to changes in the number of discrete values of terminal nodes, see for instance section 9.1.2 of Judea Pearl's classical book "Heuristics" : https://mat.uab.cat/~alseda/MasterOpt/Judea_Pearl-Heuristics_Intelligent_Search_Strategies_for_Computer_Problem_Solving.pdf Moreover, we add a small (-1, +1) random component after the quantification to help the search exploration a little bit. This is similar in spirit to the (-1, +1) random component already present in the function draw_value() to make Stockfish more robust in draw evaluations. passed STC: LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 220960 W: 57249 L: 56668 D: 107043 Ptnml(0-2): 499, 26017, 56882, 26568, 514 https://tests.stockfishchess.org/tests/view/668907fb7edfb6f233f999f8 passed LTC : LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 48966 W: 12574 L: 12233 D: 24159 Ptnml(0-2): 14, 5233, 13654, 5562, 20 https://tests.stockfishchess.org/tests/view/6689105659cb3228a47598bf closes https://github.com/official-stockfish/Stockfish/pull/5449 bench: 1336007
Copyright 2011–2024 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy Desktop Version