Dev Builds » 20240521-0613

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 06:50:51 585073 4000 1432 624 1944 +71.16 ± 5.14 3 158 878 950 11 +147.19 ± 11.49
ncm-dbt-02 06:51:54 587323 3994 1456 615 1923 +74.27 ± 4.98 1 131 903 950 12 +153.7 ± 11.29
ncm-dbt-03 06:51:36 587069 4000 1482 628 1890 +75.34 ± 4.95 1 128 897 964 10 +156.6 ± 11.33
ncm-dbt-04 06:51:56 571266 4006 1473 635 1898 +73.77 ± 5.14 1 152 878 952 20 +150.88 ± 11.48
ncm-dbt-05 06:52:42 585768 4000 1491 631 1878 +75.88 ± 4.97 1 123 907 953 16 +156.6 ± 11.25
20000 7334 3133 9533 +74.08 ± 2.25 7 692 4463 4769 69 +152.98 ± 5.08

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
385479 ncm-dbt-04 571029 6 3 0 3 +190.46 ± 18.51 0 0 0 3 0 +1199.83 ± 276.48 ↓
385478 ncm-dbt-02 588132 494 174 77 243 +69.12 ± 13.98 0 17 117 112 1 +142.53 ± 31.39 ↓
385477 ncm-dbt-05 587325 500 198 79 223 +84.3 ± 13.88 0 14 104 131 1 +178.11 ± 33.48 ↓
385476 ncm-dbt-03 586435 500 189 72 239 +82.83 ± 14.14 1 13 105 130 1 +176.33 ± 33.3 ↓
385475 ncm-dbt-01 584159 500 173 82 245 +63.95 ± 14.77 1 21 116 110 2 +130.94 ± 31.66 ↓
385474 ncm-dbt-04 573446 500 174 99 227 +52.51 ± 14.52 0 27 122 100 1 +106.01 ± 30.85 ↓
385473 ncm-dbt-02 586308 500 187 82 231 +74.06 ± 14.18 0 18 110 121 1 +153.86 ± 32.54 ↓
385472 ncm-dbt-03 585211 500 186 91 223 +66.82 ± 13.63 0 16 124 109 1 +137.37 ± 30.31 ↓
385471 ncm-dbt-05 583196 500 181 75 244 +74.79 ± 15.57 1 22 101 122 4 +152.18 ± 34.03 ↓
385470 ncm-dbt-01 585295 500 189 83 228 +74.79 ± 14.76 1 19 104 125 1 +157.24 ± 33.54 ↓
385469 ncm-dbt-04 571310 500 179 82 239 +68.27 ± 15.21 0 24 109 113 4 +135.76 ± 32.75 ↓
385468 ncm-dbt-02 586139 500 185 84 231 +71.16 ± 14.08 1 16 114 119 0 +150.51 ± 31.88 ↓
385467 ncm-dbt-03 584453 500 179 74 247 +74.06 ± 14.6 0 19 110 118 3 +150.51 ± 32.56 ↓
385466 ncm-dbt-01 581777 500 184 73 243 +78.43 ± 14.02 0 14 114 119 3 +160.64 ± 31.79 ↓
385465 ncm-dbt-05 581735 500 180 79 241 +71.16 ± 13.64 0 16 117 117 0 +148.85 ± 31.38 ↓
385464 ncm-dbt-04 571310 500 198 80 222 +83.57 ± 15.16 0 21 93 133 3 +172.78 ± 35.45 ↓
385463 ncm-dbt-02 587240 500 182 73 245 +76.97 ± 14.56 0 18 108 121 3 +157.24 ± 32.87 ↓
385462 ncm-dbt-01 584201 500 178 82 240 +67.54 ± 14.51 0 22 111 116 1 +138.99 ± 32.43 ↓
385461 ncm-dbt-03 588217 500 190 82 228 +76.25 ± 13.81 0 16 110 124 0 +160.64 ± 32.5 ↓
385460 ncm-dbt-04 571029 500 172 82 246 +63.23 ± 13.91 0 18 126 104 2 +127.76 ± 30.09 ↓
385459 ncm-dbt-05 583866 500 197 80 223 +82.83 ± 13.07 0 9 116 124 1 +174.55 ± 31.22 ↓
385458 ncm-dbt-02 590353 500 184 81 235 +72.61 ± 15.23 0 24 102 121 3 +147.19 ± 33.86 ↓
385457 ncm-dbt-01 585717 500 169 86 245 +58.21 ± 15.19 1 28 108 113 0 +121.46 ± 32.88 ↓
385456 ncm-dbt-04 570709 500 183 80 237 +72.61 ± 14.97 0 22 106 119 3 +147.19 ± 33.22 ↓
385455 ncm-dbt-05 586858 500 187 79 234 +76.25 ± 13.81 0 13 119 115 3 +155.54 ± 30.96 ↓
385454 ncm-dbt-03 588558 500 185 81 234 +73.34 ± 13.86 0 17 112 121 0 +153.86 ± 32.2 ↓
385453 ncm-dbt-02 588345 500 184 72 244 +79.17 ± 13.9 0 13 115 119 3 +162.35 ± 31.59 ↓
385452 ncm-dbt-01 586943 500 175 69 256 +74.79 ± 14.2 0 17 112 119 2 +153.86 ± 32.2 ↓
385451 ncm-dbt-04 570428 500 189 82 229 +75.52 ± 14.51 1 15 113 118 3 +155.54 ± 32.01 ↓
385450 ncm-dbt-05 587282 500 178 84 238 +66.1 ± 14.17 0 19 120 109 2 +134.15 ± 31.01 ↓
385449 ncm-dbt-03 586858 500 185 68 247 +82.83 ± 13.7 0 13 108 128 1 +174.55 ± 32.75 ↓
385448 ncm-dbt-02 585295 500 185 69 246 +82.1 ± 13.68 0 13 109 127 1 +172.78 ± 32.58 ↓
385447 ncm-dbt-01 584748 500 189 69 242 +85.04 ± 14.2 0 15 102 131 2 +178.11 ± 33.85 ↓
385446 ncm-dbt-04 570268 500 188 59 253 +91.71 ± 13.57 0 9 106 132 3 +192.71 ± 32.93 ↓
385445 ncm-dbt-05 586689 500 184 76 240 +76.25 ± 13.36 0 12 119 118 1 +158.93 ± 30.91 ↓
385444 ncm-dbt-03 589625 500 180 78 242 +71.88 ± 14.39 0 19 112 117 2 +147.19 ± 32.24 ↓
385443 ncm-dbt-02 586774 500 175 77 248 +68.99 ± 12.96 0 12 128 110 0 +143.89 ± 29.53 ↓
385442 ncm-dbt-04 571873 500 187 71 242 +82.1 ± 14.13 0 16 103 130 1 +172.78 ± 33.69 ↓
385441 ncm-dbt-01 587749 500 175 80 245 +66.82 ± 14.34 0 22 111 117 0 +138.99 ± 32.43 ↓
385440 ncm-dbt-05 589197 500 186 79 235 +75.52 ± 14.65 0 18 111 117 4 +152.18 ± 32.38 ↓
385439 ncm-dbt-03 587197 500 188 82 230 +74.79 ± 13.91 0 15 116 117 2 +153.86 ± 31.51 ↓

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
Feedback & Support Terms of Service Privacy Policy Desktop Version