Dev Builds » 20221204-1317

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 11:43:58 585881 6686 1941 1511 3234 +22.38 ± 4.04 10 558 1771 1000 4 +45.57 ± 8.07
ncm-dbt-02 11:37:49 586970 6634 1860 1546 3228 +16.46 ± 3.97 3 586 1831 888 9 +32.35 ± 7.91
ncm-dbt-03 11:37:56 587810 6680 1855 1542 3283 +16.29 ± 3.99 13 574 1846 901 6 +33.39 ± 7.87
20000 5656 4599 9745 +18.38 ± 2.31 26 1718 5448 2789 19 +37.11 ± 4.59

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
370463 ncm-dbt-02 588302 134 37 29 68 +20.77 ± 30.27 0 14 31 22 0 +41.68 ± 61.71 ↓
370462 ncm-dbt-03 589326 180 60 40 80 +38.76 ± 25.33 1 10 48 30 1 +78.52 ± 49.15 ↓
370461 ncm-dbt-01 586604 186 57 44 85 +24.32 ± 24.22 1 12 54 25 1 +48.89 ± 45.82 ↓
370460 ncm-dbt-02 585042 500 148 130 222 +12.51 ± 14.74 0 50 132 68 0 +25.06 ± 29.65 ↓
370459 ncm-dbt-03 588302 500 146 122 232 +16.69 ± 14.31 0 42 144 62 2 +30.65 ± 28.07 ↓
370458 ncm-dbt-01 585674 500 148 119 233 +20.18 ± 14.96 1 44 130 75 0 +41.89 ± 29.89 ↓
370457 ncm-dbt-02 585717 500 133 116 251 +11.82 ± 14.68 0 49 136 64 1 +22.27 ± 29.14 ↓
370456 ncm-dbt-03 588217 500 138 101 261 +25.76 ± 13.67 0 33 148 68 1 +50.38 ± 27.43 ↓
370455 ncm-dbt-01 585169 500 140 97 263 +29.95 ± 14.5 0 38 131 81 0 +60.36 ± 29.73 ↓
370454 ncm-dbt-02 588856 500 146 120 234 +18.08 ± 14.67 1 42 138 68 1 +36.26 ± 28.86 ↓
370453 ncm-dbt-03 586223 500 140 120 240 +13.91 ± 15.35 1 51 125 73 0 +29.25 ± 30.53 ↓
370452 ncm-dbt-01 586350 500 145 120 235 +17.39 ± 14.87 1 44 135 69 1 +34.86 ± 29.25 ↓
370451 ncm-dbt-02 586731 500 140 114 246 +18.08 ± 14.42 0 44 136 70 0 +36.26 ± 29.12 ↓
370450 ncm-dbt-03 586393 500 140 113 247 +18.78 ± 14.21 1 39 142 68 0 +39.08 ± 28.31 ↓
370449 ncm-dbt-01 584748 500 147 105 248 +29.25 ± 14.84 1 36 135 76 2 +57.5 ± 29.2 ↓
370448 ncm-dbt-02 586520 500 135 109 256 +18.08 ± 14.8 0 46 133 70 1 +34.86 ± 29.51 ↓
370447 ncm-dbt-03 586943 500 144 105 251 +27.15 ± 14.04 0 36 139 75 0 +54.65 ± 28.67 ↓
370446 ncm-dbt-01 585042 500 155 131 214 +16.69 ± 14.04 0 42 142 66 0 +33.46 ± 28.33 ↓
370445 ncm-dbt-02 582485 500 143 100 257 +29.95 ± 14.11 0 34 140 75 1 +58.93 ± 28.51 ↓
370444 ncm-dbt-03 587452 500 146 113 241 +22.96 ± 13.73 0 36 145 69 0 +46.13 ± 27.87 ↓
370443 ncm-dbt-01 585211 500 136 113 251 +15.99 ± 14.51 1 43 138 68 0 +33.46 ± 28.86 ↓
370442 ncm-dbt-02 585843 500 140 116 244 +16.69 ± 14.69 0 47 132 71 0 +33.46 ± 29.64 ↓
370441 ncm-dbt-03 589497 500 134 114 252 +13.91 ± 15.1 2 46 132 70 0 +30.65 ± 29.65 ↓
370440 ncm-dbt-01 587622 500 144 114 242 +20.87 ± 14.76 1 42 133 74 0 +43.3 ± 29.5 ↓
370439 ncm-dbt-02 586181 500 151 117 232 +23.66 ± 14.83 1 39 137 71 2 +46.13 ± 28.97 ↓
370438 ncm-dbt-03 587409 500 133 116 251 +11.82 ± 14.3 0 46 142 61 1 +22.27 ± 28.35 ↓
370437 ncm-dbt-01 583237 500 148 111 241 +25.76 ± 14.73 0 42 129 79 0 +51.8 ± 30.01 ↓
370436 ncm-dbt-02 587325 500 118 110 272 +5.56 ± 14.92 1 52 136 60 1 +11.12 ± 29.15 ↓
370435 ncm-dbt-03 587494 500 136 112 252 +16.69 ± 15.68 3 46 125 76 0 +37.67 ± 30.53 ↓
370434 ncm-dbt-01 585000 500 142 122 236 +13.91 ± 15.35 3 45 131 71 0 +32.05 ± 29.77 ↓
370433 ncm-dbt-02 586901 500 136 114 250 +15.3 ± 13.79 0 41 146 63 0 +30.65 ± 27.79 ↓
370432 ncm-dbt-03 588089 500 142 112 246 +20.87 ± 14.63 0 44 132 74 0 +41.89 ± 29.63 ↓
370431 ncm-dbt-01 588813 500 147 123 230 +16.69 ± 14.56 0 46 134 70 0 +33.46 ± 29.39 ↓
370430 ncm-dbt-03 586266 500 143 129 228 +9.73 ± 14.25 0 48 140 62 0 +19.48 ± 28.62 ↓
370429 ncm-dbt-01 587707 500 151 93 256 +40.48 ± 14.91 0 36 120 94 0 +82.1 ± 31.18 ↓
370428 ncm-dbt-02 586816 500 144 116 240 +19.48 ± 13.86 0 39 144 67 0 +39.08 ± 28.04 ↓
370427 ncm-dbt-01 585885 500 149 113 238 +25.06 ± 15.18 1 43 125 81 0 +51.8 ± 30.53 ↓
370426 ncm-dbt-03 589839 500 124 131 245 -4.86 ± 14.86 3 54 140 53 0 -5.56 ± 28.63 ↓
370425 ncm-dbt-02 591383 500 139 120 241 +13.21 ± 14.54 0 46 141 61 2 +23.66 ± 28.48 ↓
370424 ncm-dbt-03 587892 500 129 114 257 +10.43 ± 14.57 2 43 144 60 1 +22.27 ± 28.08 ↓
370423 ncm-dbt-02 589485 500 150 135 215 +10.43 ± 13.65 0 43 149 58 0 +20.87 ± 27.41 ↓
370422 ncm-dbt-01 585283 500 132 106 262 +18.08 ± 14.54 0 45 134 71 0 +36.26 ± 29.38 ↓

Commit

Commit ID 758f9c9350abee36a5865ec701560db8ea62004d
Author Joost VandeVondele
Date 2022-12-04 13:17:15 UTC
Stockfish 15.1 Official release version of Stockfish 15.1 Bench: 3467381 --- Today, we have the pleasure to announce Stockfish 15.1. As usual, downloads will be freely available at stockfishchess.org/download *Elo gain and competition results* With this release, version 5 of the NNUE neural net architecture has been introduced, and the training data has been extended to include Fischer random chess (FRC) positions. As a result, Elo gains are largest for FRC, reaching up to 50 Elo for doubly randomized FRC[1] (DFRC). More importantly, also for standard chess this release progressed and will win two times more game pairs than it loses[2] against Stockfish 15. Stockfish continues to win in a dominating way[3] all chess engine tournaments, including the TCEC Superfinal, Cup, FRC, DFRC, and Swiss as well as the CCC Bullet, Blitz, and Rapid events. *New evaluation* This release also introduces a new convention for the evaluation that is reported by search. An evaluation of +1 is now no longer tied to the value of one pawn, but to the likelihood of winning the game. With a +1 evaluation, Stockfish has now a 50% chance of winning the game against an equally strong opponent. This convention scales down evaluations a bit compared to Stockfish 15 and allows for consistent evaluations in the future. *ChessBase settlement* In this release period, the Stockfish team has successfully enforced its GPL license against ChessBase. This has been an intense process that included filing a lawsuit[4], a court hearing[5], and finally negotiating a settlement[6] that established that ChessBase infringed on the license by not distributing the Stockfish derivatives Fat Fritz 2 and Houdini 6 as free software, and that ensures ChessBase will respect the Free Software principles in the future. This settlement has been covered by major chess sites (see e.g. lichess.org[7] and chess.com[8]), and we are proud that it has been hailed as a ‘historic violation settlement[9]’ by the Software Freedom Conservancy. *Thank you* The Stockfish project builds on a thriving community of enthusiasts (thanks everybody!) that contribute their expertise, time, and resources to build a free and open-source chess engine that is robust, widely available, and very strong. We invite our chess fans to join the fishtest testing framework and programmers to contribute to the project[10]. The Stockfish team [1] https://tests.stockfishchess.org/tests/view/638a6170d2b9c924c4c62cb4 [2] https://tests.stockfishchess.org/tests/view/638a4dd7d2b9c924c4c6297b [3] https://en.wikipedia.org/wiki/Stockfish_(chess)#Competition_results [4] https://stockfishchess.org/blog/2021/our-lawsuit-against-chessbase/ [5] https://stockfishchess.org/blog/2022/public-court-hearing-soon/ [6] https://stockfishchess.org/blog/2022/chessbase-stockfish-agreement/ [7] https://lichess.org/blog/Y3u1mRAAACIApBVn/settlement-reached-in-stockfish-v-chessbase [8] https://www.chess.com/news/view/chessbase-stockfish-reach-settlement [9] https://sfconservancy.org/news/2022/nov/28/sfc-named-trusted-party-in-gpl-case/ [10] https://stockfishchess.org/get-involved/
Copyright 2011–2024 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy