Dev Builds » 20220412-1543

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 06:51:21 583815 4000 962 1040 1998 -6.78 ± 5.14 5 479 1107 407 2 -13.03 ± 10.18
ncm-dbt-02 06:53:25 585919 4000 946 1000 2054 -4.69 ± 5.14 3 472 1103 420 2 -9.21 ± 10.2
ncm-dbt-03 06:51:14 584403 4000 977 1030 1993 -4.6 ± 5.12 3 470 1105 421 1 -8.86 ± 10.19
ncm-dbt-04 06:52:53 568650 4002 978 1047 1977 -5.99 ± 4.97 4 447 1167 380 3 -11.81 ± 9.83
ncm-dbt-05 06:53:19 581495 3998 979 1065 1954 -7.47 ± 5.08 5 473 1125 395 1 -14.26 ± 10.07
20000 4842 5182 9976 -5.91 ± 2.28 20 2341 5607 2023 9 -11.43 ± 4.51

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
432937 ncm-dbt-04 570068 2 1 1 0 0.0 ± 34.02 0 0 1 0 0 0.0 ± 30.47 ↓
432936 ncm-dbt-05 579661 498 120 133 245 -9.07 ± 14.77 2 59 138 50 0 -15.36 ± 28.87 ↓
432935 ncm-dbt-01 582819 500 107 122 271 -10.43 ± 13.37 0 56 153 41 0 -20.87 ± 26.85 ↓
432934 ncm-dbt-02 585548 500 132 119 249 +9.04 ± 14.83 1 50 134 65 0 +19.48 ± 29.4 ↓
432933 ncm-dbt-03 584874 500 120 118 262 +1.39 ± 14.29 0 54 140 56 0 +2.78 ± 28.63 ↓
432932 ncm-dbt-04 569549 500 116 135 249 -13.21 ± 12.91 0 55 159 36 0 -26.46 ± 25.98 ↓
432931 ncm-dbt-05 581236 500 124 131 245 -4.86 ± 14.6 1 58 138 53 0 -8.34 ± 28.89 ↓
432930 ncm-dbt-01 584706 500 116 120 264 -2.78 ± 14.93 2 56 136 56 0 -2.78 ± 29.15 ↓
432929 ncm-dbt-02 588132 500 113 123 264 -6.95 ± 14.27 1 57 143 49 0 -12.51 ± 28.23 ↓
432928 ncm-dbt-03 586097 500 128 140 232 -8.34 ± 14.65 1 60 140 48 1 -16.69 ± 28.62 ↓
432927 ncm-dbt-04 569071 500 123 135 242 -8.34 ± 14.52 0 63 136 51 0 -16.69 ± 29.14 ↓
432926 ncm-dbt-05 581277 500 122 140 238 -12.51 ± 13.83 0 61 146 43 0 -25.06 ± 27.81 ↓
432925 ncm-dbt-02 586054 500 126 113 261 +9.04 ± 14.32 0 49 139 62 0 +18.08 ± 28.75 ↓
432924 ncm-dbt-03 584832 500 120 133 247 -9.03 ± 14.32 1 59 142 48 0 -16.69 ± 28.36 ↓
432923 ncm-dbt-01 582444 500 120 136 244 -11.12 ± 14.75 3 58 141 48 0 -18.08 ± 28.49 ↓
432922 ncm-dbt-04 568116 500 104 131 265 -18.78 ± 14.08 0 68 141 41 0 -37.67 ± 28.45 ↓
432921 ncm-dbt-05 583028 500 129 137 234 -5.56 ± 14.28 1 56 143 50 0 -9.73 ± 28.23 ↓
432920 ncm-dbt-04 564723 500 131 136 233 -3.48 ± 13.96 0 53 151 44 2 -9.73 ± 27.15 ↓
432919 ncm-dbt-03 582402 500 138 127 235 +7.64 ± 13.53 0 44 151 55 0 +15.3 ± 27.14 ↓
432918 ncm-dbt-01 584034 500 120 121 259 -0.69 ± 14.61 0 58 135 57 0 -1.39 ± 29.28 ↓
432917 ncm-dbt-02 586520 500 105 127 268 -15.3 ± 14.96 0 72 128 50 0 -30.65 ± 30.16 ↓
432916 ncm-dbt-04 570108 500 135 132 233 +2.09 ± 14.99 1 56 132 61 0 +5.56 ± 29.66 ↓
432915 ncm-dbt-01 585337 500 119 137 244 -12.51 ± 14.87 0 69 130 51 0 -25.06 ± 29.91 ↓
432914 ncm-dbt-05 580655 500 126 123 251 +2.09 ± 15.83 1 63 118 68 0 +5.56 ± 31.38 ↓
432913 ncm-dbt-03 583740 500 107 138 255 -21.57 ± 14.42 0 73 135 42 0 -43.3 ± 29.24 ↓
432912 ncm-dbt-02 585084 500 121 122 257 -0.7 ± 14.36 0 55 142 52 1 -2.78 ± 28.37 ↓
432911 ncm-dbt-05 579413 500 124 142 234 -12.51 ± 14.09 0 62 145 42 1 -26.46 ± 27.94 ↓
432910 ncm-dbt-01 583321 500 123 143 234 -13.9 ± 14.85 0 70 130 50 0 -27.85 ± 29.9 ↓
432909 ncm-dbt-04 569390 500 127 123 250 +2.78 ± 13.76 0 49 148 53 0 +5.56 ± 27.57 ↓
432908 ncm-dbt-03 585548 500 132 125 243 +4.86 ± 15.11 0 58 127 65 0 +9.73 ± 30.29 ↓
432907 ncm-dbt-02 584495 500 115 138 247 -15.99 ± 13.85 0 64 145 41 0 -32.05 ± 27.93 ↓
432906 ncm-dbt-05 584706 500 116 128 256 -8.34 ± 13.87 0 58 146 46 0 -16.69 ± 27.82 ↓
432905 ncm-dbt-03 584916 500 119 127 254 -5.56 ± 15.29 1 64 127 58 0 -9.73 ± 30.29 ↓
432904 ncm-dbt-01 582903 500 129 134 237 -3.47 ± 13.82 0 54 147 49 0 -6.95 ± 27.7 ↓
432903 ncm-dbt-04 567997 500 119 130 251 -7.64 ± 14.07 1 56 146 47 0 -13.9 ± 27.83 ↓
432902 ncm-dbt-02 584958 500 122 135 243 -9.04 ± 14.45 0 63 137 50 0 -18.08 ± 29.01 ↓
432901 ncm-dbt-01 584958 500 128 127 245 +0.69 ± 14.99 0 58 135 55 2 -1.39 ± 29.28 ↓
432900 ncm-dbt-03 582819 500 113 122 265 -6.25 ± 14.08 0 58 143 49 0 -12.51 ± 28.23 ↓
432899 ncm-dbt-05 581985 500 118 131 251 -9.04 ± 13.52 0 56 151 43 0 -18.08 ± 27.14 ↓
432898 ncm-dbt-04 568832 500 122 124 254 -1.39 ± 14.03 2 47 153 47 1 -1.39 ± 26.88 ↓
432897 ncm-dbt-02 586562 500 112 123 265 -7.64 ± 14.97 1 62 135 51 1 -15.3 ± 29.27 ↓

Commit

Commit ID 19a90b45bceb69aa62b5c85366343a7d1cfc695f
Author Topologist
Date 2022-04-12 15:43:50 UTC
Use NNUE in low piece endgames close to the root. This patch enforces that NNUE evaluation is used for endgame positions at shallow depth (depth <= 9). Classic evaluation will still be used for high imbalance positions when the depth is high or there are many pieces. Passed STC: https://tests.stockfishchess.org/tests/view/624c193b3a8a6ac93892dc27 LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 255840 W: 68024 L: 67362 D: 120454 Ptnml(0-2): 1074, 27089, 70926, 27763, 1068 Passed LTC: https://tests.stockfishchess.org/tests/view/624e8675e9e7821808467f77 LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 67088 W: 17784 L: 17454 D: 31850 Ptnml(0-2): 45, 6209, 20715, 6521, 54 closes https://github.com/official-stockfish/Stockfish/pull/3978 bench: 6602222
Copyright 2011–2025 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy Desktop Version