Dev Builds » 20240513-0530

You are viewing an old NCM Stockfish dev build test. You may find the most recent dev build tests using Stockfish 15 as the baseline here.

Use this dev build

NCM plays each Stockfish dev build 20,000 times against Stockfish 14. 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 11:42:06 1097156 4000 1708 343 1949 +123.52 ± 5.04 1 61 571 1306 61 +270.87 ± 14.27
ncm-dbt-02 11:41:20 1198238 3996 1782 297 1917 +135.6 ± 4.82 0 38 506 1385 69 +307.34 ± 15.16
ncm-dbt-03 11:43:49 1198640 4008 1780 288 1940 +135.86 ± 4.65 0 39 482 1435 48 +315.75 ± 15.53
ncm-dbt-05 11:40:55 1196520 3992 1767 321 1904 +131.83 ± 4.94 1 47 520 1361 67 +295.53 ± 14.95
ncm-dbt-06 11:44:08 1192471 4004 1785 343 1876 +131.0 ± 4.92 1 51 516 1373 61 +294.82 ± 15.01
20000 8822 1592 9586 +131.54 ± 2.18 3 236 2595 6860 306 +296.41 ± 6.69

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
367487 ncm-dbt-06 1191090 4 2 0 2 +190.27 ± 27.79 0 0 0 2 0 +1199.83 ± 312.71
367486 ncm-dbt-03 1199636 8 3 1 4 +88.62 ± 93.84 0 0 2 2 0 +190.67 ± 458.56
367485 ncm-dbt-05 1197411 492 215 44 233 +126.0 ± 13.75 0 6 69 165 6 +282.14 ± 41.44
367484 ncm-dbt-02 1201461 496 226 28 242 +146.85 ± 12.0 0 2 51 190 5 +361.63 ± 48.5
367483 ncm-dbt-01 1087701 500 212 43 245 +122.24 ± 13.48 0 7 71 168 4 +275.45 ± 40.84
367482 ncm-dbt-06 1187542 500 228 49 223 +130.14 ± 14.23 0 7 66 168 9 +288.06 ± 42.4
367481 ncm-dbt-03 1198488 500 226 26 248 +147.19 ± 12.78 0 5 46 193 6 +359.68 ± 51.07
367480 ncm-dbt-05 1195148 500 222 43 235 +130.15 ± 13.88 1 6 61 177 5 +301.33 ± 44.13
367479 ncm-dbt-02 1197301 500 224 38 238 +135.76 ± 14.12 0 3 71 163 13 +295.94 ± 40.69
367478 ncm-dbt-01 1098885 500 211 40 249 +123.81 ± 14.48 1 8 66 169 6 +277.93 ± 42.33
367477 ncm-dbt-03 1201968 500 217 42 241 +126.97 ± 13.22 0 6 67 173 4 +290.66 ± 42.08
367476 ncm-dbt-06 1188141 500 222 39 239 +133.34 ± 13.81 0 7 60 176 7 +304.07 ± 44.5
367475 ncm-dbt-02 1198010 500 218 30 252 +137.37 ± 13.9 0 6 59 176 9 +312.48 ± 44.93
367474 ncm-dbt-05 1199822 500 222 36 242 +135.76 ± 13.01 0 4 62 178 6 +315.35 ± 43.81
367473 ncm-dbt-01 1110807 500 214 58 228 +112.14 ± 14.53 0 11 78 155 6 +240.82 ± 38.87
367472 ncm-dbt-03 1195329 500 222 38 240 +134.15 ± 12.47 0 3 64 179 4 +315.35 ± 43.03
367471 ncm-dbt-06 1192742 500 226 42 232 +134.15 ± 13.8 0 5 65 171 9 +301.33 ± 42.75
367470 ncm-dbt-02 1195334 500 215 33 252 +132.54 ± 13.47 0 4 68 170 8 +298.62 ± 41.71
367469 ncm-dbt-05 1196265 500 211 35 254 +127.76 ± 13.92 0 4 76 160 10 +277.93 ± 39.29
367468 ncm-dbt-01 1109788 500 211 46 243 +119.11 ± 14.68 0 6 85 147 12 +247.41 ± 37.09
367467 ncm-dbt-03 1199608 500 222 32 246 +138.99 ± 14.03 0 5 61 173 11 +312.48 ± 44.19
367466 ncm-dbt-06 1197606 500 225 37 238 +137.37 ± 13.71 1 3 61 177 8 +318.25 ± 44.18
367465 ncm-dbt-05 1191446 500 228 55 217 +125.38 ± 14.47 0 7 73 160 10 +270.57 ± 40.25
367464 ncm-dbt-02 1199042 500 229 50 221 +130.14 ± 14.06 0 7 65 170 8 +290.66 ± 42.73
367463 ncm-dbt-01 1106108 500 212 41 247 +123.81 ± 14.48 0 9 69 164 8 +270.57 ± 41.4
367462 ncm-dbt-03 1199841 500 219 43 238 +127.76 ± 14.1 0 5 74 161 10 +277.93 ± 39.92
367461 ncm-dbt-06 1191922 500 218 45 237 +125.38 ± 14.63 0 7 74 158 11 +268.17 ± 39.97
367460 ncm-dbt-05 1197538 500 227 36 237 +139.81 ± 14.01 0 6 57 177 10 +318.25 ± 45.73
367459 ncm-dbt-02 1195510 500 220 35 245 +134.95 ± 14.31 0 8 58 175 9 +304.07 ± 45.19
367458 ncm-dbt-03 1197233 500 228 32 240 +143.89 ± 12.92 0 3 56 183 8 +339.63 ± 46.2
367457 ncm-dbt-01 1100279 500 222 37 241 +134.95 ± 13.78 0 5 64 172 9 +304.07 ± 43.1
367456 ncm-dbt-06 1194133 500 221 43 236 +129.35 ± 14.58 0 10 60 172 8 +288.06 ± 44.27
367455 ncm-dbt-05 1196691 500 215 31 254 +134.15 ± 14.15 0 5 67 167 11 +295.94 ± 42.08
367454 ncm-dbt-03 1194624 500 220 34 246 +135.76 ± 13.01 0 7 53 187 3 +324.17 ± 47.35
367453 ncm-dbt-02 1194548 500 228 41 231 +136.56 ± 13.55 0 4 64 173 9 +309.64 ± 43.08
367452 ncm-dbt-01 1089734 500 211 39 250 +124.6 ± 14.14 0 8 69 166 7 +275.45 ± 41.43
367451 ncm-dbt-06 1194492 500 221 46 233 +126.97 ± 13.76 0 6 70 167 7 +282.94 ± 41.13
367450 ncm-dbt-01 1073946 500 215 39 246 +127.76 ± 14.27 0 7 69 165 9 +280.42 ± 41.44
367449 ncm-dbt-05 1197839 500 227 41 232 +135.76 ± 14.47 0 9 55 177 9 +306.84 ± 46.27
367448 ncm-dbt-02 1204699 500 222 42 236 +130.94 ± 13.51 0 4 70 168 8 +293.29 ± 41.07
367447 ncm-dbt-03 1201036 500 223 40 237 +133.34 ± 12.49 0 5 59 184 2 +318.25 ± 44.96
367446 ncm-dbt-06 1194578 500 222 42 236 +130.94 ± 12.76 0 6 60 182 2 +309.64 ± 44.55

Commit

Commit ID 0b08953174d222270100690b45fad0dc47c01f98
Author Linmiao Xu
Date 2024-05-13 05:30:18 UTC
Re-evaluate some small net positions for more accurate evals Use main net evals when small net evals hint that higher eval accuracy may be worth the slower eval speeds. With Finny caches, re-evals with the main net are less expensive than before. Original idea by mstembera who I've added as co-author to this PR. Based on reEval tests by mstembera: https://tests.stockfishchess.org/tests/view/65e69187b6345c1b934866e5 https://tests.stockfishchess.org/tests/view/65e863aa0ec64f0526c3e991 A few variants of this patch also passed LTC: https://tests.stockfishchess.org/tests/view/663d2108507ebe1c0e91f407 https://tests.stockfishchess.org/tests/view/663e388c3a2f9702074bc152 Passed STC: https://tests.stockfishchess.org/tests/view/663dadbd1a61d6377f190e2c LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 92320 W: 23941 L: 23531 D: 44848 Ptnml(0-2): 430, 10993, 22931, 11349, 457 Passed LTC: https://tests.stockfishchess.org/tests/view/663ef48b2948bf9aa698690c LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 98934 W: 24907 L: 24457 D: 49570 Ptnml(0-2): 48, 10952, 27027, 11382, 58 closes https://github.com/official-stockfish/Stockfish/pull/5238 bench 1876282 Co-Authored-By: mstembera <5421953+mstembera@users.noreply.github.com>
Copyright 2011–2024 Next Chess Move LLC