Dev Builds » 20230715-0716

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 09:43:40 1176943 3278 1392 313 1573 +118.78 ± 5.55 1 55 488 1054 41 +259.86 ± 15.44
ncm-dbt-02 10:57:55 1234524 3680 1578 320 1782 +123.75 ± 5.07 1 42 544 1204 49 +273.98 ± 14.6
ncm-dbt-03 09:43:09 1232821 3276 1359 299 1618 +116.61 ± 5.55 1 61 488 1053 35 +255.51 ± 15.43
ncm-dbt-04 09:40:09 1222525 3270 1374 279 1617 +121.01 ± 5.46 0 44 498 1047 46 +264.35 ± 15.27
ncm-dbt-05 09:32:55 1230467 3224 1375 291 1558 +121.54 ± 5.61 1 41 499 1015 56 +262.44 ± 15.25
ncm-dbt-06 09:42:50 1223829 3272 1363 278 1631 +119.74 ± 5.45 1 47 493 1056 39 +263.4 ± 15.35
20000 8441 1780 9779 +120.3 ± 2.22 5 290 3010 6429 266 +263.42 ± 6.21

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
196627 ncm-dbt-02 1231252 180 75 11 94 +129.17 ± 21.47 0 2 23 64 1 +301.33 ± 73.63
196626 ncm-dbt-05 1235394 224 90 24 110 +105.49 ± 23.85 0 5 43 57 7 +203.49 ± 52.55
196625 ncm-dbt-04 1216484 270 118 21 131 +130.64 ± 19.08 0 2 40 87 6 +284.26 ± 54.68
196624 ncm-dbt-06 1223926 272 113 20 139 +123.77 ± 18.7 0 4 38 91 3 +276.54 ± 56.36
196623 ncm-dbt-01 1134568 278 118 15 145 +135.15 ± 17.68 0 3 33 100 3 +314.93 ± 60.81
196622 ncm-dbt-03 1220606 276 120 29 127 +118.99 ± 19.0 0 4 43 87 4 +257.84 ± 52.77
196621 ncm-dbt-02 1224996 500 212 57 231 +111.37 ± 14.06 0 8 85 151 6 +238.66 ± 37.17
196620 ncm-dbt-05 1227569 500 210 46 244 +118.33 ± 13.7 0 8 74 164 4 +263.42 ± 39.97
196619 ncm-dbt-04 1232072 500 210 40 250 +123.02 ± 13.99 0 9 67 169 5 +275.45 ± 42.01
196618 ncm-dbt-06 1234935 500 199 52 249 +105.25 ± 13.88 1 8 86 153 2 +232.26 ± 36.96
196617 ncm-dbt-03 1226581 500 196 46 258 +107.54 ± 14.05 0 8 90 146 6 +228.08 ± 36.04
196616 ncm-dbt-01 1210758 500 223 42 235 +131.74 ± 13.12 0 4 67 173 6 +301.33 ± 42.04
196615 ncm-dbt-02 1223284 500 207 39 254 +121.45 ± 13.49 0 6 75 164 5 +270.57 ± 39.67
196614 ncm-dbt-05 1239625 500 222 45 233 +128.55 ± 15.08 0 6 76 153 15 +268.17 ± 39.39
196613 ncm-dbt-04 1227738 500 202 42 256 +115.22 ± 14.37 0 10 76 158 6 +249.64 ± 39.41
196612 ncm-dbt-03 1243911 500 219 40 241 +130.14 ± 13.52 0 6 65 173 6 +295.94 ± 42.75
196611 ncm-dbt-01 1134906 500 214 45 241 +122.24 ± 14.82 0 8 76 155 11 +258.75 ± 39.42
196610 ncm-dbt-06 1221598 500 216 41 243 +126.97 ± 13.22 0 4 73 167 6 +285.49 ± 40.16
196609 ncm-dbt-02 1234047 500 217 45 238 +124.6 ± 13.97 0 4 80 156 10 +268.17 ± 38.21
196608 ncm-dbt-05 1240704 500 211 50 239 +116.0 ± 14.85 1 7 81 152 9 +247.41 ± 38.13
196607 ncm-dbt-04 1234276 500 201 50 249 +108.3 ± 14.05 0 7 92 144 7 +228.08 ± 35.56
196606 ncm-dbt-03 1238809 500 212 54 234 +113.68 ± 14.22 0 10 77 158 5 +247.41 ± 39.15
196605 ncm-dbt-06 1232206 500 199 41 260 +113.68 ± 13.38 0 5 87 153 5 +247.41 ± 36.56
196604 ncm-dbt-01 1189775 500 209 43 248 +119.89 ± 14.02 0 7 77 159 7 +261.07 ± 39.14
196603 ncm-dbt-02 1230954 500 217 40 243 +128.55 ± 13.91 1 6 63 175 5 +295.94 ± 43.42
196602 ncm-dbt-05 1222542 500 213 43 244 +123.02 ± 13.82 0 6 75 162 7 +270.57 ± 39.67
196601 ncm-dbt-04 1219834 500 209 44 247 +119.11 ± 13.52 0 6 78 161 5 +263.42 ± 38.85
196600 ncm-dbt-01 1198333 500 205 59 236 +104.49 ± 14.19 0 13 80 155 2 +228.08 ± 38.34
196599 ncm-dbt-03 1253762 500 189 39 272 +107.54 ± 15.13 1 12 79 152 6 +230.16 ± 38.58
196598 ncm-dbt-06 1214213 500 198 41 261 +112.91 ± 13.89 0 7 85 152 6 +243.0 ± 37.13
196597 ncm-dbt-02 1253344 500 217 51 232 +119.89 ± 13.85 0 6 79 158 7 +261.07 ± 38.58
196596 ncm-dbt-05 1243217 500 212 47 241 +119.11 ± 13.34 0 5 80 160 5 +263.42 ± 38.27
196595 ncm-dbt-04 1229331 500 221 48 231 +125.38 ± 14.63 0 6 77 155 12 +265.78 ± 39.12
196594 ncm-dbt-06 1228460 500 215 45 240 +123.02 ± 14.82 0 10 69 162 9 +265.78 ± 41.36
196593 ncm-dbt-01 1171543 500 214 57 229 +112.91 ± 14.53 1 10 74 161 4 +249.64 ± 39.91
196592 ncm-dbt-03 1223661 500 212 54 234 +113.68 ± 14.05 0 9 79 157 5 +247.41 ± 38.64
196591 ncm-dbt-02 1237253 500 206 36 258 +123.02 ± 13.65 0 6 74 164 6 +273.0 ± 39.95
196590 ncm-dbt-05 1204220 500 217 36 247 +131.74 ± 13.67 0 4 70 167 9 +293.29 ± 41.07
196589 ncm-dbt-04 1197943 500 213 34 253 +130.14 ± 12.97 0 4 68 173 5 +298.62 ± 41.71
196588 ncm-dbt-06 1211467 500 223 38 239 +134.95 ± 14.31 0 9 55 178 8 +306.84 ± 46.27
196587 ncm-dbt-03 1222417 500 211 37 252 +126.17 ± 14.12 0 12 55 180 3 +290.66 ± 45.85
196586 ncm-dbt-01 1198719 500 209 52 239 +112.91 ± 14.69 0 10 81 151 8 +238.66 ± 38.15
196585 ncm-dbt-02 1241068 500 227 41 232 +135.76 ± 13.57 0 4 65 172 9 +306.84 ± 42.73

Commit

Commit ID ee53f8ed2f9418b55b05811da93ddf62f03c255f
Author Linmiao Xu
Date 2023-07-15 07:16:09 UTC
Reintroduce nnue eval pawn count multipliers again With separate multipliers for nnue eval and optimism scaling. This patch used 4 out of 7 params tuned with spsa at 30+0.3 using this tuning config: Value LazyThreshold1 = Value(3622); Value LazyThreshold2 = Value(1962); int psqThresh = 2048; int nnueNpmBase = 945; int nnuePcMult = 0; int optNpmBase = 150; int optPcMult = 0; TUNE(SetRange(3322, 3922), LazyThreshold1); TUNE(SetRange(1662, 2262), LazyThreshold2); TUNE(SetRange(1748, 2348), psqThresh); TUNE(SetRange(745, 1145), nnueNpmBase); TUNE(SetRange(-16, 16), nnuePcMult); TUNE(SetRange(0, 300), optNpmBase); TUNE(SetRange(-16, 16), optPcMult); Passed STC: https://tests.stockfishchess.org/tests/view/64a5a9b402cd07745c60ed07 LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 173632 W: 44417 L: 43903 D: 85312 Ptnml(0-2): 547, 20025, 45068, 20719, 457 Passed LTC: https://tests.stockfishchess.org/tests/view/64a972a302cd07745c6136af LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 277644 W: 70955 L: 70147 D: 136542 Ptnml(0-2): 193, 29902, 77787, 30784, 156 closes https://github.com/official-stockfish/Stockfish/pull/4681 bench 1556301
Copyright 2011–2024 Next Chess Move LLC