Dev Builds » 20250817-2035

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 06:42:32 583176 4000 1674 479 1847 +107.06 ± 4.84 2 65 692 1218 23 +233.85 ± 12.94
ncm-dbt-02 06:43:44 586647 3996 1635 459 1902 +105.36 ± 4.67 1 55 722 1207 13 +231.52 ± 12.63
ncm-dbt-03 06:44:16 583317 4014 1634 421 1959 +108.38 ± 4.68 0 66 670 1263 8 +241.04 ± 13.15
ncm-dbt-04 06:43:41 568379 4016 1658 447 1911 +108.13 ± 4.64 2 48 710 1233 15 +238.99 ± 12.73
ncm-dbt-05 06:44:01 579309 3974 1612 441 1921 +105.5 ± 4.74 0 62 709 1199 17 +230.57 ± 12.76
20000 8213 2247 9540 +106.89 ± 2.11 5 296 3503 6120 76 +235.18 ± 5.74

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
428041 ncm-dbt-04 568315 16 7 2 7 +112.26 ± 65.75 0 0 3 5 0 +254.61 ± 287.37
428040 ncm-dbt-03 584411 14 4 2 8 +49.93 ± 60.15 0 0 5 2 0 +102.04 ± 134.61
428039 ncm-dbt-05 581943 474 179 59 236 +89.91 ± 13.5 0 9 99 129 0 +193.79 ± 34.15
428038 ncm-dbt-02 586266 496 199 49 248 +108.46 ± 13.12 0 8 82 158 0 +243.46 ± 37.88
428037 ncm-dbt-01 583321 500 213 56 231 +112.91 ± 13.39 0 7 82 158 3 +249.64 ± 37.86
428036 ncm-dbt-04 566336 500 214 62 224 +109.07 ± 13.05 0 7 85 157 1 +243.0 ± 37.13
428035 ncm-dbt-03 582068 500 192 55 253 +97.69 ± 13.66 0 11 92 146 1 +211.87 ± 35.7
428034 ncm-dbt-05 576823 500 202 59 239 +102.22 ± 13.54 0 10 88 151 1 +223.94 ± 36.53
428033 ncm-dbt-02 586223 500 204 51 245 +109.83 ± 13.05 0 5 90 152 3 +240.82 ± 35.87
428032 ncm-dbt-01 582527 500 201 62 237 +99.2 ± 15.33 2 14 80 151 3 +215.85 ± 38.24
428031 ncm-dbt-04 570348 500 209 56 235 +109.83 ± 13.56 0 9 81 158 2 +243.0 ± 38.14
428030 ncm-dbt-03 582444 500 211 46 243 +119.11 ± 12.62 0 5 76 168 1 +273.0 ± 39.35
428029 ncm-dbt-05 583531 500 204 52 244 +109.07 ± 13.4 0 8 84 156 2 +240.82 ± 37.4
428028 ncm-dbt-02 585928 500 210 55 235 +111.37 ± 13.73 0 7 86 152 5 +240.82 ± 36.9
428027 ncm-dbt-01 584832 500 212 64 224 +106.01 ± 13.05 0 6 92 150 2 +232.26 ± 35.5
428026 ncm-dbt-04 568196 500 201 49 250 +109.07 ± 13.4 0 9 81 159 1 +243.0 ± 38.14
428025 ncm-dbt-03 582945 500 210 57 233 +109.83 ± 13.23 0 9 79 162 0 +247.41 ± 38.64
428024 ncm-dbt-05 581985 500 202 55 243 +105.25 ± 12.71 0 3 100 144 3 +228.08 ± 33.59
428023 ncm-dbt-02 585928 500 195 50 255 +103.73 ± 13.87 0 11 85 152 2 +226.0 ± 37.21
428022 ncm-dbt-01 582444 500 211 57 232 +110.6 ± 13.73 0 9 81 157 3 +243.0 ± 38.14
428021 ncm-dbt-03 580530 500 208 47 245 +116.0 ± 13.71 0 11 68 170 1 +263.42 ± 41.6
428020 ncm-dbt-04 568951 500 215 54 231 +116.0 ± 13.02 1 3 82 162 2 +263.42 ± 37.69
428019 ncm-dbt-05 575924 500 210 63 227 +105.25 ± 13.88 0 10 86 151 3 +228.08 ± 36.98
428018 ncm-dbt-02 587367 500 212 68 220 +102.97 ± 12.53 0 3 102 143 2 +223.94 ± 33.2
428017 ncm-dbt-01 583572 500 214 58 228 +112.14 ± 13.56 0 7 84 155 4 +245.2 ± 37.37
428016 ncm-dbt-04 568077 500 201 65 234 +96.94 ± 13.16 0 7 102 139 2 +207.95 ± 33.55
428015 ncm-dbt-03 581485 500 198 59 243 +99.2 ± 13.19 0 9 93 148 0 +217.85 ± 35.44
428014 ncm-dbt-05 576823 500 204 48 248 +112.14 ± 12.69 0 5 85 159 1 +251.89 ± 37.03
428013 ncm-dbt-01 582152 500 207 62 231 +103.73 ± 14.19 0 12 84 151 3 +223.94 ± 37.43
428012 ncm-dbt-02 586266 500 205 70 225 +96.19 ± 13.95 1 10 93 145 1 +209.91 ± 35.49
428011 ncm-dbt-04 570148 500 210 54 236 +112.14 ± 13.56 1 5 84 157 3 +249.64 ± 37.33
428010 ncm-dbt-03 586266 500 195 52 253 +102.22 ± 13.21 0 7 95 146 2 +221.9 ± 34.93
428009 ncm-dbt-05 576169 500 206 59 235 +105.25 ± 13.72 0 9 88 150 3 +228.08 ± 36.51
428008 ncm-dbt-02 587877 500 204 59 237 +103.73 ± 12.7 0 6 93 151 0 +230.16 ± 35.29
428007 ncm-dbt-01 581735 500 208 57 235 +108.3 ± 13.4 0 5 94 146 5 +232.26 ± 35.0
428006 ncm-dbt-04 567878 500 206 53 241 +109.83 ± 13.05 0 5 90 152 3 +240.82 ± 35.87
428005 ncm-dbt-03 585759 500 203 55 242 +106.01 ± 13.56 0 9 86 153 2 +232.26 ± 36.96
428004 ncm-dbt-02 587325 500 206 57 237 +106.77 ± 12.53 0 5 91 154 0 +238.66 ± 35.65
428003 ncm-dbt-05 581277 500 205 46 249 +114.45 ± 13.72 0 8 79 159 4 +251.89 ± 38.63
428002 ncm-dbt-03 583950 500 213 48 239 +119.11 ± 12.62 0 5 76 168 1 +273.0 ± 39.35
428001 ncm-dbt-01 584832 500 208 63 229 +103.73 ± 12.53 0 5 95 150 0 +230.16 ± 34.79
428000 ncm-dbt-04 567165 500 195 52 253 +102.22 ± 12.35 0 3 102 144 1 +223.94 ± 33.2

Commit

Commit ID c56bd10cb5ba192c76b6c5c6228625d58bd99892
Author Stefan Geschwentner
Date 2025-08-17 20:35:03 UTC
Fix undefined behavior in stalemate trap detection. An important part of it is a function which detects if we can move a king or pawn. If this function called before quiet move generation phase the end of the checked move list is undefined (Thanks to AliceRoselia pointing out we have some problem because of wrong bench in a test). This problem exists also in master but is really rarely triggered (thanks to vondele which found one) but it seen significant more often if the capture order score is increased. This fix now simply assumes in this case (and other similiar cases) that a king or pawn can move without checking any moves. Passed non-regression STC (with default book): LLR: 3.03 (-2.94,2.94) <-1.75,0.25> Total: 203008 W: 52465 L: 52424 D: 98119 Ptnml(0-2): 498, 20293, 59893, 20310, 510 https://tests.stockfishchess.org/tests/view/68a06ec5fd8719b088c8dc1a Passed non-regression STC (with stalemates book): LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 31616 W: 14418 L: 14366 D: 2832 Ptnml(0-2): 1, 189, 15375, 243, 0 https://tests.stockfishchess.org/tests/view/68a07538fd8719b088c8dc1f closes https://github.com/official-stockfish/Stockfish/pull/6235 Bench: 2996176
Copyright 2011–2025 Next Chess Move LLC