Dev Builds » 20220705-1155

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 06:54:26 581375 4000 1118 952 1930 +14.43 ± 5.15 3 363 1107 519 8 +28.03 ± 10.17
ncm-dbt-02 06:55:55 586408 4018 1112 989 1917 +10.64 ± 5.09 5 373 1130 496 5 +21.3 ± 10.05
ncm-dbt-03 06:54:19 584392 4000 1082 987 1931 +8.25 ± 5.16 6 388 1118 481 7 +16.34 ± 10.11
ncm-dbt-04 06:55:45 568955 4008 1127 1004 1877 +10.67 ± 5.11 2 379 1125 490 8 +20.31 ± 10.07
ncm-dbt-05 06:56:18 580423 3974 1090 951 1933 +12.16 ± 5.3 6 389 1058 528 6 +24.34 ± 10.45
20000 5529 4883 9588 +11.23 ± 2.31 22 1892 5538 2514 34 +22.06 ± 4.55

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
415768 ncm-dbt-04 569151 8 3 1 4 +88.62 ± 93.84 0 0 2 2 0 +190.67 ± 458.56 ↓
415767 ncm-dbt-02 588004 18 7 5 6 +38.73 ± 48.22 0 0 7 2 0 +78.47 ± 102.62 ↓
415766 ncm-dbt-05 581985 474 115 112 247 +2.2 ± 15.68 0 58 118 61 0 +4.4 ± 31.43 ↓
415765 ncm-dbt-01 579578 500 144 131 225 +9.03 ± 14.19 0 46 147 55 2 +15.3 ± 27.69 ↓
415764 ncm-dbt-03 584958 500 137 116 247 +14.6 ± 14.65 0 47 136 66 1 +27.85 ± 29.13 ↓
415763 ncm-dbt-04 566612 500 140 120 240 +13.91 ± 14.98 1 48 131 70 0 +29.25 ± 29.78 ↓
415762 ncm-dbt-02 587155 500 142 118 240 +16.69 ± 14.31 0 43 141 65 1 +32.05 ± 28.47 ↓
415761 ncm-dbt-05 579001 500 147 113 240 +23.66 ± 15.08 1 40 136 70 3 +44.72 ± 29.1 ↓
415760 ncm-dbt-01 580904 500 141 117 242 +16.69 ± 15.56 1 51 121 77 0 +34.86 ± 31.03 ↓
415759 ncm-dbt-04 570029 500 136 132 232 +2.78 ± 14.67 1 53 137 59 0 +6.95 ± 29.02 ↓
415758 ncm-dbt-03 583656 500 134 124 242 +6.95 ± 14.4 0 51 138 61 0 +13.9 ± 28.89 ↓
415757 ncm-dbt-02 587113 500 131 126 243 +3.48 ± 14.48 1 51 140 58 0 +8.34 ± 28.63 ↓
415756 ncm-dbt-05 578465 500 138 116 246 +15.3 ± 13.79 0 41 146 63 0 +30.65 ± 27.79 ↓
415755 ncm-dbt-01 581902 500 136 125 239 +7.64 ± 14.2 0 48 144 57 1 +13.9 ± 28.1 ↓
415754 ncm-dbt-04 569789 500 143 119 238 +16.69 ± 14.69 0 47 132 71 0 +33.46 ± 29.64 ↓
415753 ncm-dbt-03 584453 500 129 112 259 +11.82 ± 15.06 0 53 127 70 0 +23.66 ± 30.28 ↓
415752 ncm-dbt-02 586266 500 144 125 231 +13.21 ± 14.28 0 45 142 62 1 +25.06 ± 28.35 ↓
415751 ncm-dbt-05 582068 500 132 113 255 +13.21 ± 13.89 0 43 145 62 0 +26.46 ± 27.94 ↓
415750 ncm-dbt-01 579042 500 142 111 247 +21.57 ± 14.55 0 42 136 71 1 +41.89 ± 29.11 ↓
415749 ncm-dbt-04 568116 500 137 130 233 +4.86 ± 14.35 0 51 142 56 1 +8.34 ± 28.37 ↓
415748 ncm-dbt-03 585717 500 134 128 238 +4.17 ± 14.41 2 45 150 51 2 +8.34 ± 27.29 ↓
415747 ncm-dbt-02 586223 500 128 110 262 +12.51 ± 14.61 0 49 134 67 0 +25.06 ± 29.4 ↓
415746 ncm-dbt-05 581610 500 135 114 251 +14.6 ± 15.28 0 51 129 68 2 +26.46 ± 30.03 ↓
415745 ncm-dbt-01 583447 500 144 117 239 +18.78 ± 14.34 0 41 143 64 2 +34.86 ± 28.19 ↓
415744 ncm-dbt-04 566651 500 142 137 221 +3.47 ± 13.82 0 48 150 51 1 +5.56 ± 27.29 ↓
415743 ncm-dbt-03 583866 500 140 117 243 +15.99 ± 13.58 1 36 152 61 0 +33.46 ± 26.95 ↓
415742 ncm-dbt-02 585548 500 142 120 238 +15.3 ± 13.93 0 42 144 64 0 +30.65 ± 28.07 ↓
415741 ncm-dbt-05 577684 500 148 124 228 +16.69 ± 15.56 2 48 124 76 0 +36.26 ± 30.66 ↓
415740 ncm-dbt-01 581527 500 145 122 233 +15.99 ± 14.12 0 43 141 66 0 +32.05 ± 28.47 ↓
415739 ncm-dbt-04 570469 500 140 124 236 +11.12 ± 13.84 0 43 149 57 1 +20.87 ± 27.41 ↓
415738 ncm-dbt-03 585253 500 134 126 240 +5.56 ± 15.77 2 55 128 63 2 +11.12 ± 30.16 ↓
415737 ncm-dbt-02 586562 500 135 126 239 +6.25 ± 14.72 2 47 142 58 1 +13.9 ± 28.36 ↓
415736 ncm-dbt-01 583782 500 126 112 262 +9.73 ± 14.51 0 49 139 61 1 +18.08 ± 28.75 ↓
415735 ncm-dbt-05 578794 500 132 126 242 +4.17 ± 15.05 0 57 131 61 1 +6.95 ± 29.79 ↓
415734 ncm-dbt-04 569989 500 146 124 230 +15.3 ± 14.32 0 42 147 58 3 +26.46 ± 27.67 ↓
415733 ncm-dbt-02 586689 500 151 133 216 +12.51 ± 14.99 2 45 137 65 1 +26.46 ± 29.0 ↓
415732 ncm-dbt-03 582277 500 133 127 240 +4.17 ± 14.54 1 50 142 56 1 +8.34 ± 28.37 ↓
415731 ncm-dbt-01 580821 500 140 117 243 +15.99 ± 15.02 2 43 136 68 1 +33.46 ± 29.13 ↓
415730 ncm-dbt-03 584958 500 141 137 222 +2.78 ± 14.16 0 51 145 53 1 +4.17 ± 27.97 ↓
415729 ncm-dbt-05 583782 500 143 133 224 +6.95 ± 15.52 3 51 129 67 0 +18.08 ± 30.03 ↓
415728 ncm-dbt-04 569789 500 140 117 243 +15.99 ± 14.89 0 47 135 66 2 +29.25 ± 29.26 ↓
415727 ncm-dbt-02 584117 500 132 126 242 +4.17 ± 14.28 0 51 143 55 1 +6.95 ± 28.24 ↓

Commit

Commit ID c2aaaa65f97d4cd5fc06f19ce8d158d85dcd7a7b
Author Michael Chaly
Date 2022-07-05 11:55:50 UTC
Simplify away FRC correction term Since new net is trained partially using FRC data this part of adjustment that penalises bishops that are locked in the corner is no longer needed - net should "know" this things itself much better. STC on FRC book : https://tests.stockfishchess.org/tests/view/62c3031b9e7d9997a12d852f LLR: 2.96 (-2.94,2.94) <-2.25,0.25> Total: 22048 W: 3003 L: 2845 D: 16200 Ptnml(0-2): 96, 1778, 7149, 1874, 127 LTC on FRC book : https://tests.stockfishchess.org/tests/view/62c32e939e7d9997a12d8c5e LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 36784 W: 3138 L: 3037 D: 30609 Ptnml(0-2): 36, 1842, 14537, 1939, 38 STC on DFRC book : https://tests.stockfishchess.org/tests/view/62c32efb9e7d9997a12d8c6f LLR: 2.94 (-2.94,2.94) <-2.25,0.25> Total: 20424 W: 3903 L: 3721 D: 12800 Ptnml(0-2): 172, 1984, 5724, 2154, 178 LTC on DFRC book : https://tests.stockfishchess.org/tests/view/62c358c79e7d9997a12d9319 LLR: 2.93 (-2.94,2.94) <-2.25,0.25> Total: 53784 W: 7581 L: 7480 D: 38723 Ptnml(0-2): 87, 3887, 18856, 3962, 100 closes https://github.com/official-stockfish/Stockfish/pull/4101 bench 5182295
Copyright 2011–2025 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy Desktop Version