Dev Builds » 20260402-1830

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 06:42:30 583421 4000 1729 366 1905 +123.32 ± 4.52 0 30 605 1337 28 +280.11 ± 13.8
ncm-dbt-02 06:43:02 585602 4002 1742 390 1870 +122.17 ± 4.52 0 33 607 1337 24 +277.72 ± 13.79
ncm-dbt-03 06:43:53 584897 4008 1743 357 1908 +125.31 ± 4.67 0 43 568 1357 36 +283.99 ± 14.3
ncm-dbt-04 06:42:46 566353 4000 1743 377 1880 +123.61 ± 4.47 0 32 591 1356 21 +283.26 ± 13.98
ncm-dbt-05 06:44:43 582282 3990 1725 354 1911 +124.44 ± 4.45 0 25 599 1346 25 +284.65 ± 13.86
20000 8682 1844 9474 +123.77 ± 2.02 0 163 2970 6733 134 +281.93 ± 6.23

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
464732 ncm-dbt-02 587197 2 0 0 2 0.0 ± 34.02 0 0 1 0 0 0.0 ± 30.47 ↓
464731 ncm-dbt-03 585000 8 3 1 4 +88.62 ± 93.84 0 0 2 2 0 +190.67 ± 458.56 ↓
464730 ncm-dbt-05 579744 490 218 42 230 +130.61 ± 12.73 0 0 76 162 7 +294.47 ± 38.78 ↓
464729 ncm-dbt-04 565233 500 216 43 241 +125.39 ± 12.32 0 5 67 178 0 +295.94 ± 42.08 ↓
464728 ncm-dbt-01 583321 500 222 39 239 +133.34 ± 12.89 0 5 61 180 4 +312.48 ± 44.19 ↓
464727 ncm-dbt-03 584327 500 211 42 247 +122.24 ± 13.83 0 8 70 167 5 +273.0 ± 41.13 ↓
464726 ncm-dbt-02 586139 500 217 59 224 +113.68 ± 12.31 0 4 84 162 0 +258.75 ± 37.2 ↓
464725 ncm-dbt-01 582652 500 221 43 236 +129.35 ± 13.17 0 5 67 173 5 +295.94 ± 42.08 ↓
464724 ncm-dbt-05 581485 500 211 33 256 +129.35 ± 12.21 0 2 71 174 3 +301.33 ± 40.6 ↓
464723 ncm-dbt-03 585885 500 215 48 237 +120.67 ± 12.78 0 4 78 165 3 +273.0 ± 38.74 ↓
464722 ncm-dbt-04 566454 500 222 36 242 +135.76 ± 11.36 0 1 63 185 1 +330.23 ± 43.2 ↓
464721 ncm-dbt-02 585801 500 219 53 228 +119.89 ± 13.33 0 4 82 158 6 +263.42 ± 37.69 ↓
464720 ncm-dbt-05 583321 500 221 48 231 +125.38 ± 13.43 0 7 67 172 4 +285.49 ± 42.08 ↓
464719 ncm-dbt-01 583363 500 214 48 238 +119.89 ± 12.98 0 4 80 162 4 +268.17 ± 38.21 ↓
464718 ncm-dbt-04 566770 500 207 51 242 +112.14 ± 12.69 0 3 91 153 3 +247.41 ± 35.47 ↓
464717 ncm-dbt-03 584916 500 218 49 233 +122.24 ± 13.66 0 6 75 163 6 +270.57 ± 39.67 ↓
464716 ncm-dbt-02 585421 500 220 46 234 +126.17 ± 13.06 0 6 67 174 3 +290.66 ± 42.08 ↓
464715 ncm-dbt-01 584495 500 216 52 232 +118.33 ± 12.44 0 3 82 163 2 +268.17 ± 37.61 ↓
464714 ncm-dbt-05 584790 500 213 38 249 +126.96 ± 11.46 0 0 76 173 1 +298.62 ± 38.82 ↓
464713 ncm-dbt-02 583531 500 215 45 240 +123.02 ± 12.74 0 5 72 171 2 +282.94 ± 40.5 ↓
464712 ncm-dbt-03 584706 500 220 57 223 +117.55 ± 13.18 0 5 81 160 4 +261.07 ± 38.02 ↓
464711 ncm-dbt-04 566809 500 214 44 242 +123.02 ± 13.11 0 6 71 170 3 +280.42 ± 40.83 ↓
464710 ncm-dbt-01 582027 500 212 51 237 +116.0 ± 12.66 0 5 80 164 1 +263.42 ± 38.27 ↓
464709 ncm-dbt-05 582444 500 216 50 234 +119.89 ± 12.42 0 3 80 165 2 +273.0 ± 38.12 ↓
464708 ncm-dbt-03 584958 500 215 39 246 +127.76 ± 13.02 0 6 65 176 3 +295.94 ± 42.75 ↓
464707 ncm-dbt-02 586774 500 210 38 252 +124.6 ± 12.71 0 4 73 170 3 +285.49 ± 40.16 ↓
464706 ncm-dbt-04 564997 500 217 55 228 +116.77 ± 12.28 0 2 86 160 2 +263.42 ± 36.51 ↓
464705 ncm-dbt-01 583279 500 215 42 243 +125.38 ± 12.32 0 2 76 169 3 +288.06 ± 39.11 ↓
464704 ncm-dbt-03 585548 500 216 40 244 +127.76 ± 13.39 0 5 70 169 6 +288.06 ± 41.11 ↓
464703 ncm-dbt-05 581444 500 215 42 243 +125.38 ± 13.07 0 3 77 164 6 +280.42 ± 38.93 ↓
464702 ncm-dbt-02 587409 500 217 48 235 +122.24 ± 12.57 0 2 81 163 4 +275.45 ± 37.75 ↓
464701 ncm-dbt-04 564135 500 222 52 226 +123.02 ± 13.29 0 6 72 168 4 +277.93 ± 40.53 ↓
464700 ncm-dbt-01 584243 500 215 44 241 +123.81 ± 12.92 0 1 84 158 7 +273.0 ± 36.86 ↓
464699 ncm-dbt-02 583154 500 218 52 230 +119.89 ± 12.61 0 2 84 160 4 +268.17 ± 36.99 ↓
464698 ncm-dbt-03 585000 500 229 42 229 +136.56 ± 12.79 0 3 63 178 6 +318.25 ± 43.39 ↓
464697 ncm-dbt-05 585042 500 214 43 243 +123.81 ± 12.35 0 4 72 173 1 +288.06 ± 40.46 ↓
464696 ncm-dbt-04 567601 500 221 55 224 +119.89 ± 13.16 0 5 78 163 4 +268.17 ± 38.8 ↓
464695 ncm-dbt-02 585000 500 226 49 225 +128.55 ± 12.82 0 6 63 179 2 +301.33 ± 43.45 ↓
464694 ncm-dbt-01 583992 500 214 47 239 +120.67 ± 12.78 0 5 75 168 2 +275.45 ± 39.63 ↓
464693 ncm-dbt-04 568832 500 224 41 235 +133.34 ± 12.69 0 4 63 179 4 +312.48 ± 43.44 ↓
464692 ncm-dbt-03 583740 500 216 39 245 +128.55 ± 13.01 0 6 64 177 3 +298.62 ± 43.1 ↓
464691 ncm-dbt-05 579992 500 217 58 225 +114.45 ± 12.85 0 6 80 163 1 +258.75 ± 38.32 ↓

Commit

Commit ID f614ff90e21e0898008ac8e676d134abd5f7c679
Author Linmiao Xu
Date 2026-04-02 18:30:26 UTC
Neon dotprod speedup in sparse-input affine transform Also apply VNNI accumulator splitting strategy to NEON dotprod. Speedup measured locally with profile-build, apple-silicon M3 Pro: ``` Result of 20 runs ================== base (...kfish-master) = 1582485 +/- 12985 test (...parse-affine) = 1605204 +/- 13801 diff = +22720 +/- 1212 speedup = +0.0144 P(speedup > 0) = 1.0000 CPU: 11 x arm Hyperthreading: off ``` Passed STC: https://tests.stockfishchess.org/tests/view/69c04c71f690a4b7f5fb0cde LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 80576 W: 20748 L: 20391 D: 39437 Ptnml(0-2): 161, 8472, 22658, 8843, 154 closes https://github.com/official-stockfish/Stockfish/pull/6682 No functional change
Copyright 2011–2026 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy Desktop Version