Dev Builds » 20260504-0631

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 06:39:49 582810 4000 1783 333 1884 +131.94 ± 4.37 1 19 536 1417 27 +309.64 ± 14.67
ncm-dbt-02 06:40:21 585916 4014 1768 333 1913 +129.95 ± 4.45 0 27 548 1402 30 +301.37 ± 14.53
ncm-dbt-03 06:41:22 584918 4014 1786 338 1890 +131.24 ± 4.36 1 15 556 1405 30 +306.16 ± 14.38
ncm-dbt-04 06:40:10 567311 4000 1733 347 1920 +125.58 ± 4.5 0 33 573 1369 25 +288.39 ± 14.21
ncm-dbt-05 06:39:41 581050 3972 1773 314 1885 +133.87 ± 4.45 1 19 522 1408 36 +313.21 ± 14.88
20000 8843 1665 9492 +130.5 ± 1.98 3 113 2735 7001 148 +303.59 ± 6.49

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
467779 ncm-dbt-02 586435 14 7 2 5 +129.72 ± 68.06 0 0 2 5 0 +311.09 ± 530.6
467778 ncm-dbt-03 583321 14 4 0 10 +102.04 ± 70.73 0 0 3 4 0 +225.59 ± 263.0
467777 ncm-dbt-05 583950 472 196 34 242 +124.29 ± 12.97 0 4 68 162 2 +286.75 ± 41.67
467776 ncm-dbt-04 566336 500 224 37 239 +136.56 ± 12.39 0 3 61 182 4 +324.17 ± 44.15
467775 ncm-dbt-01 583908 500 219 36 245 +133.34 ± 11.67 0 1 67 180 2 +318.25 ± 41.77
467774 ncm-dbt-02 584664 500 214 40 246 +126.17 ± 13.06 0 4 73 168 5 +285.49 ± 40.16
467773 ncm-dbt-03 584034 500 230 44 226 +135.76 ± 12.81 0 1 70 171 8 +309.64 ± 40.79
467772 ncm-dbt-05 574297 500 233 43 224 +138.99 ± 13.1 1 3 56 185 5 +333.32 ± 46.21
467771 ncm-dbt-04 570068 500 223 49 228 +126.17 ± 12.68 0 4 71 172 3 +290.66 ± 40.76
467770 ncm-dbt-02 584453 500 215 47 238 +121.45 ± 12.77 0 5 74 169 2 +277.93 ± 39.92
467769 ncm-dbt-01 582861 500 229 47 224 +132.54 ± 13.1 0 4 66 174 6 +304.07 ± 42.38
467768 ncm-dbt-03 583321 500 228 42 230 +135.76 ± 12.42 0 2 65 178 5 +318.25 ± 42.59
467767 ncm-dbt-05 580075 500 220 38 242 +132.54 ± 13.28 0 6 61 178 5 +306.84 ± 44.17
467766 ncm-dbt-04 569829 500 211 40 249 +123.81 ± 12.54 0 3 76 168 3 +282.94 ± 39.21
467765 ncm-dbt-02 587028 500 233 34 233 +146.36 ± 12.18 0 2 53 189 6 +356.21 ± 47.52
467764 ncm-dbt-01 584622 500 219 41 240 +129.35 ± 12.61 1 2 67 178 2 +306.84 ± 41.99
467763 ncm-dbt-03 586604 500 220 43 237 +128.55 ± 12.24 0 1 75 170 4 +295.94 ± 39.27
467762 ncm-dbt-05 582235 500 217 40 243 +128.55 ± 12.43 0 2 73 171 4 +295.94 ± 39.99
467761 ncm-dbt-04 564958 500 222 45 233 +128.55 ± 13.56 0 6 67 171 6 +290.66 ± 42.08
467760 ncm-dbt-02 587240 500 229 41 230 +137.37 ± 12.15 0 1 65 179 5 +324.17 ± 42.47
467759 ncm-dbt-01 582652 500 227 41 232 +135.76 ± 12.62 0 1 69 173 7 +312.48 ± 41.11
467758 ncm-dbt-03 583740 500 218 56 226 +116.77 ± 13.01 0 4 84 158 4 +258.75 ± 37.2
467757 ncm-dbt-05 583405 500 232 45 223 +136.56 ± 12.79 0 2 66 175 7 +315.35 ± 42.24
467756 ncm-dbt-02 584874 500 210 53 237 +112.91 ± 13.22 0 6 84 157 3 +249.64 ± 37.33
467755 ncm-dbt-04 567442 500 212 36 252 +127.76 ± 12.84 0 7 61 181 1 +301.33 ± 44.13
467754 ncm-dbt-01 582318 500 218 52 230 +119.89 ± 12.79 0 5 76 167 2 +273.0 ± 39.35
467753 ncm-dbt-03 586477 500 226 34 240 +140.62 ± 11.59 0 1 59 187 3 +342.85 ± 44.76
467752 ncm-dbt-05 581818 500 230 32 238 +145.54 ± 12.22 0 0 60 182 8 +346.11 ± 44.19
467751 ncm-dbt-02 584285 500 223 33 244 +138.99 ± 11.88 0 2 59 186 3 +336.46 ± 44.87
467750 ncm-dbt-04 564527 500 212 40 248 +124.6 ± 12.53 0 3 75 169 3 +285.49 ± 39.5
467749 ncm-dbt-03 587367 500 217 44 239 +125.38 ± 12.12 0 2 75 171 2 +290.66 ± 39.4
467748 ncm-dbt-01 580987 500 224 35 241 +138.18 ± 11.91 0 2 60 185 3 +333.32 ± 44.47
467747 ncm-dbt-05 578630 500 223 43 234 +130.94 ± 12.17 0 1 72 173 4 +304.07 ± 40.16
467746 ncm-dbt-02 586604 500 219 38 243 +131.74 ± 12.34 0 2 69 175 4 +306.84 ± 41.23
467745 ncm-dbt-04 569310 500 210 50 240 +115.22 ± 12.85 0 5 82 161 2 +258.75 ± 37.76
467744 ncm-dbt-03 581444 500 223 32 245 +139.81 ± 12.05 1 1 56 190 2 +346.12 ± 46.15
467743 ncm-dbt-01 582861 500 222 42 236 +130.94 ± 11.55 0 2 66 182 0 +315.35 ± 42.24
467742 ncm-dbt-05 583992 500 222 39 239 +133.34 ± 11.46 0 1 66 182 1 +321.19 ± 42.12
467741 ncm-dbt-02 587664 500 218 45 237 +125.38 ± 12.7 0 5 69 174 2 +290.66 ± 41.43
467740 ncm-dbt-01 582277 500 225 39 236 +135.76 ± 12.42 0 2 65 178 5 +318.25 ± 42.59
467739 ncm-dbt-03 587962 500 220 43 237 +128.55 ± 12.24 0 3 69 176 2 +301.33 ± 41.33
467738 ncm-dbt-04 566020 500 219 50 231 +122.24 ± 12.38 0 2 80 165 3 +277.93 ± 38.02

Commit

Commit ID 3e3e976fdf54adf6fce636ff21f7c0f4ce66a70a
Author Robert Nurnberg @ elitebook
Date 2026-05-04 06:31:06 UTC
[bugfix] Respect bound flags for searched moves in multiPV analysis Master in `pv()` incorrectly assumes that any root move with `i != pvIdx` has an exact score. This can lead to the suppression of bound flags for (a) root moves that have been partially searched in an iteration but do not end up to be best move, or (b) when an aborted search for `pvIdx > 0` leads to a new best move. This latter case is the cause for issue #6783. Fixes #6783. The bug in its incarnation (a) was independently discovered by @ciekce a couple of weeks ago, and we have jointly discussed a patch that fixes it. He is therefore a co-author of the bugfix part of this patch. While at it, we also fix three minor oversights in the PV roll-back for aborted searches with a loss score: * We only roll back the PV if the aborted search would report an exact score. * Master inadvertently may have reported a bound for the rolled-back score+PV. * We ensure a final UCI info line with the correct search depth and searched nodes statistics etc. closes https://github.com/official-stockfish/Stockfish/pull/6784 No functional change Co-Authored-By: Ciekce <44617491+Ciekce@users.noreply.github.com>
Copyright 2011–2026 Next Chess Move LLC