Dev Builds » 20240723-1724

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 04:21:55 584878 2548 994 362 1192 +88.01 ± 6.0 1 53 540 673 7 +186.87 ± 14.57
ncm-dbt-02 12:51:30 581317 7458 2845 1064 3549 +84.6 ± 3.64 5 204 1546 1953 21 +178.7 ± 8.64
ncm-dbt-03 12:47:46 579667 7434 2773 1042 3619 +82.41 ± 3.64 3 211 1577 1904 22 +173.04 ± 8.55
ncm-dbt-04 00:55:29 569246 520 194 73 253 +82.35 ± 13.9 0 17 106 136 1 +173.46 ± 33.21
ncm-dbt-05 03:33:05 593220 2040 769 269 1002 +86.92 ± 6.84 0 50 428 534 8 +182.77 ± 16.41
20000 7575 2810 9615 +84.4 ± 2.21 9 535 4197 5200 59 +177.89 ± 5.24

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
371195 ncm-dbt-04 566217 20 7 3 10 +70.4 ± 55.57 0 0 6 4 0 +147.13 ± 135.14
371194 ncm-dbt-05 585126 40 13 2 25 +98.04 ± 41.25 0 0 9 11 0 +214.81 ± 116.48
371193 ncm-dbt-01 582110 48 18 7 23 +81.04 ± 36.73 0 0 13 11 0 +172.02 ± 90.98
371192 ncm-dbt-02 588004 464 168 72 224 +72.94 ± 14.42 0 16 104 112 0 +152.93 ± 33.43
371191 ncm-dbt-03 590353 470 179 80 211 +74.29 ± 14.5 0 16 105 113 1 +154.29 ± 33.27
371190 ncm-dbt-04 572276 500 187 70 243 +82.83 ± 14.29 0 17 100 132 1 +174.55 ± 34.22
371189 ncm-dbt-01 587494 500 205 71 224 +95.44 ± 14.1 1 11 92 145 1 +207.95 ± 35.71
371188 ncm-dbt-05 589582 500 198 62 240 +96.94 ± 13.65 0 9 99 139 3 +206.01 ± 34.24
371187 ncm-dbt-02 585674 500 180 85 235 +66.82 ± 14.48 0 22 112 115 1 +137.37 ± 32.27
371186 ncm-dbt-03 587622 500 189 82 229 +75.52 ± 13.34 0 12 120 117 1 +157.24 ± 30.75
371185 ncm-dbt-02 587877 500 183 72 245 +78.44 ± 13.42 1 10 116 123 0 +167.53 ± 31.34
371184 ncm-dbt-03 586774 500 174 70 256 +73.34 ± 13.42 0 14 118 118 0 +153.86 ± 31.15
371183 ncm-dbt-05 586393 500 198 59 243 +99.2 ± 13.67 0 8 99 139 4 +209.91 ± 34.19
371182 ncm-dbt-02 586943 500 196 63 241 +94.69 ± 13.78 0 11 97 140 2 +202.15 ± 34.7
371181 ncm-dbt-03 586816 500 192 55 253 +97.69 ± 14.43 0 14 88 145 3 +207.95 ± 36.54
371180 ncm-dbt-05 583698 500 185 71 244 +80.63 ± 13.18 0 11 114 125 0 +171.02 ± 31.66
371179 ncm-dbt-02 584369 500 193 65 242 +90.97 ± 14.62 1 13 96 137 3 +192.71 ± 34.94
371178 ncm-dbt-03 586646 500 186 65 249 +85.78 ± 14.51 0 17 97 134 2 +179.9 ± 34.76
371177 ncm-dbt-05 621303 500 175 75 250 +70.43 ± 14.62 0 22 107 120 1 +145.54 ± 33.06
371176 ncm-dbt-03 468438 500 181 67 252 +80.63 ± 14.23 0 17 103 129 1 +169.27 ± 33.7
371175 ncm-dbt-02 504890 500 193 63 244 +92.45 ± 14.05 0 12 99 136 3 +194.57 ± 34.34
371174 ncm-dbt-03 587155 464 180 56 228 +95.16 ± 14.81 1 10 87 132 2 +205.12 ± 36.72
371173 ncm-dbt-02 588472 494 192 74 228 +84.62 ± 13.69 0 13 103 131 0 +180.68 ± 33.62
371172 ncm-dbt-03 585843 500 174 62 264 +79.17 ± 13.9 0 15 109 125 1 +165.8 ± 32.64
371171 ncm-dbt-02 587367 500 188 67 245 +85.78 ± 14.22 0 16 98 135 1 +181.7 ± 34.58
371170 ncm-dbt-03 589027 500 178 66 256 +79.17 ± 14.34 0 16 109 122 3 +162.35 ± 32.67
371169 ncm-dbt-02 585970 500 199 69 232 +92.45 ± 14.2 0 15 91 143 1 +198.34 ± 35.92
371168 ncm-dbt-03 586604 500 183 67 250 +82.1 ± 13.52 0 13 108 129 0 +174.55 ± 32.75
371167 ncm-dbt-02 588345 500 194 81 225 +79.9 ± 13.77 1 10 116 121 2 +167.53 ± 31.34
371166 ncm-dbt-03 587749 500 194 69 237 +88.74 ± 14.28 1 13 97 138 1 +190.85 ± 34.75
371165 ncm-dbt-02 587962 500 200 72 228 +90.96 ± 14.02 0 13 98 137 2 +192.71 ± 34.55
371164 ncm-dbt-03 586477 500 188 79 233 +76.98 ± 13.98 1 13 113 122 1 +162.35 ± 31.95
371163 ncm-dbt-02 586223 500 192 68 240 +88.0 ± 13.97 0 13 102 133 2 +185.33 ± 33.81
371162 ncm-dbt-01 584537 500 196 80 224 +82.1 ± 13.98 0 14 108 126 2 +171.02 ± 32.78
371161 ncm-dbt-03 588047 500 186 73 241 +79.9 ± 13.77 0 13 113 122 2 +165.8 ± 31.92
371160 ncm-dbt-02 586774 500 192 79 229 +79.9 ± 14.21 1 13 110 124 2 +167.53 ± 32.45
371159 ncm-dbt-01 584453 500 194 68 238 +89.48 ± 12.89 0 8 108 134 0 +192.71 ± 32.52
371158 ncm-dbt-03 588643 500 187 70 243 +82.83 ± 13.7 0 13 108 128 1 +174.55 ± 32.75
371157 ncm-dbt-02 585590 500 190 70 240 +85.04 ± 14.35 0 16 100 132 2 +178.11 ± 34.22
371156 ncm-dbt-01 585169 500 191 63 246 +90.96 ± 13.08 0 8 107 134 1 +194.57 ± 32.69
371155 ncm-dbt-02 585295 500 185 64 251 +85.78 ± 13.77 1 11 104 134 0 +185.33 ± 33.42
371154 ncm-dbt-01 585506 500 190 73 237 +82.83 ± 13.85 0 12 112 123 3 +171.02 ± 32.04
371153 ncm-dbt-03 588813 500 202 81 217 +85.78 ± 14.36 0 15 102 130 3 +178.11 ± 33.85

Commit

Commit ID 1e2f0511033945d07e1c8856980ed72cdbe42822
Author Linmiao Xu
Date 2024-07-23 17:24:00 UTC
Replace simple eval with psqt in re-eval condition As a result, re-eval depends only on smallnet outputs so an extra call to simple eval can be removed. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/669743054ff211be9d4ec232 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 214912 W: 55801 L: 55777 D: 103334 Ptnml(0-2): 746, 24597, 56760, 24593, 760 https://github.com/official-stockfish/Stockfish/pull/5501 Bench: 1440277
Copyright 2011–2024 Next Chess Move LLC