Dev Builds » 20240521-0613

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 11:38:31 1202323 4002 1759 311 1932 +131.67 +/- 4.79 1 37 535 1369 59 +297.71 +/- 14.73
ncm-dbt-02 11:37:29 1218745 4000 1782 317 1901 +133.44 +/- 4.57 0 22 543 1383 52 +305.8 +/- 14.58
ncm-dbt-03 11:39:01 1227377 4012 1801 314 1897 +135.21 +/- 4.73 0 31 522 1388 65 +307.45 +/- 14.91
ncm-dbt-05 11:37:33 1196861 3986 1752 324 1910 +130.25 +/- 4.87 2 43 530 1361 57 +293.89 +/- 14.81
ncm-dbt-06 11:39:43 1232676 4000 1787 307 1906 +134.95 +/- 4.74 1 29 523 1383 64 +307.19 +/- 14.89
20000 8881 1573 9546 +133.1 +/- 2.12 4 162 2653 6884 297 +302.36 +/- 6.61

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
368479 ncm-dbt-02 1206328 0 0 0 0 -0.0 +/- 1199.83 0 0 0 0 0 -0.0 +/- 1199.83
368478 ncm-dbt-06 1234830 0 0 0 0 -0.0 +/- 1199.83 0 0 0 0 0 -0.0 +/- 1199.83
368477 ncm-dbt-01 1239697 2 1 1 0 0.0 +/- 34.02 0 0 1 0 0 0.0 +/- 30.47
368476 ncm-dbt-03 1228548 12 4 2 6 +58.43 +/- 110.55 0 1 2 3 0 +120.41 +/- 334.55
368475 ncm-dbt-05 1199107 486 223 52 211 +127.7 +/- 14.19 0 8 62 167 6 +287.43 +/- 43.72
368474 ncm-dbt-02 1222950 500 223 37 240 +135.76 +/- 12.62 0 2 66 176 6 +315.35 +/- 42.24
368473 ncm-dbt-06 1205124 500 231 41 228 +138.99 +/- 14.74 1 4 62 170 13 +309.64 +/- 43.82
368472 ncm-dbt-01 1180488 500 230 40 230 +138.99 +/- 13.67 0 7 53 183 7 +324.17 +/- 47.35
368471 ncm-dbt-03 1220901 500 221 42 237 +130.14 +/- 12.97 0 3 71 170 6 +295.94 +/- 40.69
368470 ncm-dbt-05 1194365 500 209 43 248 +119.89 +/- 13.51 0 5 80 159 6 +263.42 +/- 38.27
368469 ncm-dbt-06 1230385 500 223 38 239 +134.95 +/- 13.59 0 3 69 168 10 +301.33 +/- 41.33
368468 ncm-dbt-02 1209084 500 222 31 247 +139.81 +/- 12.67 0 3 59 182 6 +330.23 +/- 44.94
368467 ncm-dbt-01 1220532 500 215 40 245 +126.97 +/- 14.78 1 7 67 166 9 +280.42 +/- 42.05
368466 ncm-dbt-03 1229315 500 220 36 244 +134.15 +/- 12.67 0 1 71 171 7 +306.84 +/- 40.47
368465 ncm-dbt-05 1199659 500 228 45 227 +133.34 +/- 13.26 0 3 69 170 8 +301.33 +/- 41.33
368464 ncm-dbt-06 1235410 500 231 52 217 +130.14 +/- 13.7 0 5 69 168 8 +290.66 +/- 41.43
368463 ncm-dbt-01 1210533 500 228 44 228 +134.15 +/- 13.8 0 4 68 168 10 +298.62 +/- 41.71
368462 ncm-dbt-03 1234004 500 231 31 238 +147.19 +/- 13.18 0 4 51 186 9 +349.43 +/- 48.52
368461 ncm-dbt-02 1199352 500 234 39 227 +143.07 +/- 13.34 0 2 62 175 11 +327.18 +/- 43.69
368460 ncm-dbt-05 1193531 500 225 30 245 +143.07 +/- 13.15 0 2 61 177 10 +330.23 +/- 44.08
368459 ncm-dbt-06 1240483 500 218 33 249 +134.95 +/- 13.22 0 4 64 175 7 +309.64 +/- 43.08
368458 ncm-dbt-01 1192531 500 224 42 234 +132.54 +/- 14.01 0 6 65 170 9 +295.94 +/- 42.75
368457 ncm-dbt-02 1215140 500 222 44 234 +129.35 +/- 13.36 0 5 68 171 6 +293.29 +/- 41.75
368456 ncm-dbt-03 1223686 500 234 33 233 +148.02 +/- 12.94 0 1 58 180 11 +346.12 +/- 45.18
368455 ncm-dbt-05 1195219 500 207 31 262 +127.76 +/- 13.92 0 8 64 172 6 +288.06 +/- 43.03
368454 ncm-dbt-06 1255170 500 211 26 263 +134.95 +/- 13.03 0 6 57 183 4 +318.25 +/- 45.73
368453 ncm-dbt-01 1211104 500 216 36 248 +130.94 +/- 12.76 0 2 72 170 6 +298.62 +/- 40.29
368452 ncm-dbt-03 1214126 500 220 35 245 +134.95 +/- 13.22 0 5 61 178 6 +312.48 +/- 44.19
368451 ncm-dbt-02 1215578 500 220 36 244 +134.15 +/- 12.47 0 3 64 179 4 +315.35 +/- 43.03
368450 ncm-dbt-05 1197969 500 221 48 231 +125.39 +/- 13.79 1 4 72 167 6 +282.94 +/- 40.5
368449 ncm-dbt-06 1243117 500 226 38 236 +137.37 +/- 11.94 0 1 64 181 4 +327.18 +/- 42.83
368448 ncm-dbt-01 1162738 500 215 33 252 +132.54 +/- 13.28 0 3 70 169 8 +298.62 +/- 41.01
368447 ncm-dbt-02 1234866 500 225 42 233 +133.34 +/- 13.08 0 3 68 172 7 +304.07 +/- 41.65
368446 ncm-dbt-03 1240072 500 219 48 233 +123.81 +/- 14.15 0 8 70 165 7 +273.0 +/- 41.13
368445 ncm-dbt-05 1195138 500 223 33 244 +138.99 +/- 13.29 0 4 60 178 8 +321.19 +/- 44.57
368444 ncm-dbt-06 1219554 500 225 49 226 +127.76 +/- 13.57 0 3 77 161 9 +280.42 +/- 38.93
368443 ncm-dbt-03 1230163 500 226 45 229 +131.74 +/- 12.93 0 3 69 172 6 +301.33 +/- 41.33
368442 ncm-dbt-01 1180674 500 218 34 248 +134.15 +/- 13.24 0 3 68 171 8 +304.07 +/- 41.65
368441 ncm-dbt-02 1218085 500 220 39 241 +131.74 +/- 12.74 0 3 68 174 5 +304.07 +/- 41.65
368440 ncm-dbt-06 1230014 500 222 30 248 +140.62 +/- 13.24 0 3 61 177 9 +324.17 +/- 44.15
368439 ncm-dbt-03 1225581 500 226 42 232 +134.15 +/- 14.5 0 5 69 163 13 +290.66 +/- 41.43
368438 ncm-dbt-02 1247322 500 216 49 235 +120.67 +/- 12.97 0 1 88 154 7 +263.42 +/- 35.9
368437 ncm-dbt-01 1222617 500 212 41 247 +123.81 +/- 12.73 0 5 71 172 2 +285.49 +/- 40.81
368436 ncm-dbt-05 1199906 500 216 42 242 +126.18 +/- 14.79 1 9 62 171 7 +282.94 +/- 43.58

Commit

Commit ID 4d88a63e607f44e59b9cc56b45984937e5eb123c
Author Linmiao Xu
Date 2024-05-21 06:13:25 UTC
Re-eval only if smallnet output flips from simple eval Recent attempts to change the smallnet nnue re-eval threshold did not show much elo difference: https://tests.stockfishchess.org/tests/view/664a29bb25a9058c4d21d53c https://tests.stockfishchess.org/tests/view/664a299925a9058c4d21d53a Passed non-regression STC: https://tests.stockfishchess.org/tests/view/664a3ea95fc7b70b8817aee2 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 22304 W: 5905 L: 5664 D: 10735 Ptnml(0-2): 67, 2602, 5603, 2783, 97 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/664a43d35fc7b70b8817aef4 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 37536 W: 9667 L: 9460 D: 18409 Ptnml(0-2): 25, 4090, 10321, 4317, 15 closes https://github.com/official-stockfish/Stockfish/pull/5271 bench 1287409
Copyright 2011–2024 Next Chess Move LLC