Dev Builds » 20240311-0904

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 06:50:39 577728 4000 1493 561 1946 +82.47 ± 4.94 2 107 862 1015 14 +172.78 ± 11.55
ncm-dbt-02 06:53:14 586082 4010 1484 564 1962 +81.16 ± 4.97 2 115 864 1009 15 +169.44 ± 11.55
ncm-dbt-03 06:52:55 583795 4012 1504 616 1892 +78.19 ± 4.92 1 122 878 998 7 +163.93 ± 11.46
ncm-dbt-04 06:52:06 568582 4000 1495 573 1932 +81.55 ± 4.85 0 107 873 1011 9 +171.24 ± 11.47
ncm-dbt-05 06:53:28 580382 3978 1502 595 1881 +80.63 ± 4.96 1 113 867 994 14 +168.17 ± 11.52
20000 7478 2909 9613 +80.8 ± 2.2 6 564 4344 5027 59 +169.1 ± 5.14

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
418582 ncm-dbt-03 581652 12 3 3 6 -0.0 ± 117.89 0 2 2 2 0 -0.0 ± 271.37
418581 ncm-dbt-02 587240 10 4 0 6 +147.05 ± 74.68 0 0 1 4 0 +381.35 ± 516.06
418580 ncm-dbt-05 578465 478 180 73 225 +79.11 ± 15.39 0 22 89 127 1 +165.59 ± 36.2
418579 ncm-dbt-02 586520 500 184 75 241 +76.97 ± 14.7 0 18 109 119 4 +155.54 ± 32.7
418578 ncm-dbt-01 577438 500 188 81 231 +75.52 ± 13.64 1 11 119 118 1 +158.93 ± 30.91
418577 ncm-dbt-04 569310 500 183 75 242 +76.25 ± 13.05 0 10 123 116 1 +158.93 ± 30.17
418576 ncm-dbt-03 581943 500 193 77 230 +82.1 ± 13.68 0 12 112 124 2 +171.02 ± 32.04
418575 ncm-dbt-05 584706 500 185 75 240 +77.7 ± 14.0 0 16 109 124 1 +162.35 ± 32.67
418574 ncm-dbt-04 566612 500 184 68 248 +82.1 ± 13.37 0 12 110 128 0 +174.55 ± 32.38
418573 ncm-dbt-03 586223 500 196 73 231 +87.26 ± 14.1 0 15 98 136 1 +185.33 ± 34.57
418572 ncm-dbt-01 578630 500 187 68 245 +84.31 ± 13.58 0 13 105 132 0 +179.9 ± 33.27
418571 ncm-dbt-02 585674 500 185 63 252 +86.52 ± 14.23 1 11 106 129 3 +181.7 ± 33.07
418570 ncm-dbt-05 579207 500 193 76 231 +82.83 ± 14.14 0 14 108 125 3 +171.02 ± 32.78
418569 ncm-dbt-02 582235 500 193 70 237 +87.26 ± 14.1 0 14 101 133 2 +183.51 ± 34.01
418568 ncm-dbt-04 569589 500 189 65 246 +88.0 ± 13.81 0 12 104 132 2 +185.33 ± 33.42
418567 ncm-dbt-03 585674 500 186 66 248 +85.04 ± 14.05 0 15 101 133 1 +179.9 ± 34.03
418566 ncm-dbt-01 578095 500 179 59 262 +85.04 ± 13.9 0 13 106 129 2 +178.11 ± 33.1
418565 ncm-dbt-05 576823 500 193 74 233 +84.31 ± 14.03 1 11 108 128 2 +178.11 ± 32.72
418564 ncm-dbt-04 567442 500 177 79 244 +68.99 ± 14.42 0 22 108 120 0 +143.89 ± 32.9
418563 ncm-dbt-02 585295 500 185 63 252 +86.52 ± 14.08 0 15 99 135 1 +183.51 ± 34.39
418562 ncm-dbt-03 583740 500 195 82 223 +79.9 ± 14.07 0 16 106 127 1 +167.53 ± 33.17
418561 ncm-dbt-01 576987 500 189 83 228 +74.79 ± 13.76 0 15 115 119 1 +155.54 ± 31.67
418560 ncm-dbt-05 579331 500 186 67 247 +84.3 ± 13.11 0 9 114 126 1 +178.11 ± 31.55
418559 ncm-dbt-03 582778 500 184 72 244 +79.17 ± 14.34 0 17 106 125 2 +164.07 ± 33.19
418558 ncm-dbt-02 586604 500 183 67 250 +82.1 ± 13.98 0 14 108 126 2 +171.02 ± 32.78
418557 ncm-dbt-04 569151 500 198 66 236 +93.95 ± 14.38 0 15 90 143 2 +200.24 ± 36.12
418556 ncm-dbt-01 579661 500 193 62 245 +93.2 ± 14.36 0 13 97 136 4 +194.57 ± 34.74
418555 ncm-dbt-05 579083 500 180 89 231 +63.94 ± 14.23 0 20 121 107 2 +129.35 ± 30.88
418554 ncm-dbt-04 566375 500 192 77 231 +81.36 ± 13.51 0 12 112 125 1 +171.02 ± 32.04
418553 ncm-dbt-03 582652 500 177 77 246 +70.44 ± 13.01 0 12 126 112 0 +147.19 ± 29.83
418552 ncm-dbt-02 588515 500 193 78 229 +81.36 ± 13.35 0 11 114 124 1 +171.02 ± 31.66
418551 ncm-dbt-01 577028 500 185 69 246 +82.1 ± 13.83 0 14 107 128 1 +172.78 ± 32.96
418550 ncm-dbt-05 577438 500 190 59 251 +93.2 ± 13.12 0 7 107 134 2 +198.34 ± 32.63
418549 ncm-dbt-02 586774 500 180 69 251 +78.44 ± 14.74 1 17 104 126 2 +164.07 ± 33.53
418548 ncm-dbt-03 584706 500 179 86 235 +65.39 ± 14.28 1 19 116 114 0 +137.37 ± 31.63
418547 ncm-dbt-04 570029 500 190 77 233 +79.9 ± 13.47 0 12 114 123 1 +167.53 ± 31.71
418546 ncm-dbt-01 579124 500 190 80 230 +77.71 ± 14.58 1 15 110 121 3 +160.64 ± 32.5
418545 ncm-dbt-01 574865 500 182 59 259 +87.26 ± 13.95 0 13 103 132 2 +183.51 ± 33.63
418544 ncm-dbt-03 584790 500 191 80 229 +78.44 ± 13.58 0 14 111 125 0 +165.8 ± 32.28
418543 ncm-dbt-02 585885 500 177 79 244 +68.99 ± 13.41 0 15 122 113 0 +143.89 ± 30.58
418542 ncm-dbt-05 588004 500 195 82 223 +79.9 ± 13.92 0 14 111 123 2 +165.8 ± 32.28
418541 ncm-dbt-04 570148 500 182 66 252 +82.1 ± 13.68 0 12 112 124 2 +171.02 ± 32.04

Commit

Commit ID 10e27329783c9f92bad8b7bd7fe496382a7fc0cd
Author Muzhen Gaming
Date 2024-03-11 09:04:37 UTC
VVLTC search tune Result of 32k games of tuning at 60+0.6 8-thread. Link to the tuning attempt: https://tests.stockfishchess.org/tests/view/65def7b04b19edc854ebdec8 Passed VVLTC first SPRT: https://tests.stockfishchess.org/tests/view/65e51b53416ecd92c162ab7f LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 37570 W: 9613 L: 9342 D: 18615 Ptnml(0-2): 2, 3454, 11601, 3727, 1 Passed VVLTC second SPRT: https://tests.stockfishchess.org/tests/view/65e87d1c0ec64f0526c3eb39 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 123158 W: 31463 L: 31006 D: 60689 Ptnml(0-2): 5, 11589, 37935, 12044, 6 Note: The small net and psqt-only thresholds have been moved to evaluate.h. The reasoning is that these values are used in both `evaluate.cpp` and `evaluate_nnue.cpp`, and thus unifying their usage avoids inconsistencies during testing, where one occurrence is changed without the other (this happened during the search tune SPRT). closes https://github.com/official-stockfish/Stockfish/pull/5101 Bench: 1741218
Copyright 2011–2025 Next Chess Move LLC