Dev Builds » 20260905-0802

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 06:47:01 583349 3986 1787 283 1916 +137.91 ± 4.45 0 22 488 1440 43 +324.96 ± 15.41
ncm-dbt-02 06:46:22 590959 4000 1848 299 1853 +141.95 ± 4.48 0 23 457 1468 52 +336.85 ± 15.94
ncm-dbt-03 06:46:56 582286 4000 1793 311 1896 +135.15 ± 4.43 0 13 539 1401 47 +313.55 ± 14.6
ncm-dbt-04 06:49:00 566780 4016 1811 295 1910 +137.98 ± 4.52 0 30 477 1456 45 +324.59 ± 15.61
ncm-dbt-05 06:47:09 604375 3998 1814 287 1897 +139.78 ± 4.43 1 18 478 1457 45 +331.67 ± 15.57
20000 9053 1475 9472 +138.55 ± 1.99 1 106 2439 7222 232 +326.19 ± 6.88

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
484454 ncm-dbt-04 569270 16 8 2 6 +136.89 ± 61.78 0 0 2 6 0 +337.87 ± 515.83
484453 ncm-dbt-01 584916 486 225 36 225 +142.62 ± 13.22 0 3 56 176 8 +333.99 ± 46.18
484452 ncm-dbt-03 581735 500 214 45 241 +122.24 ± 13.3 0 3 82 158 7 +268.17 ± 37.61
484451 ncm-dbt-05 602516 498 216 43 239 +125.93 ± 12.53 0 3 73 170 3 +289.83 ± 40.08
484450 ncm-dbt-02 593802 500 225 33 242 +140.62 ± 11.59 0 1 59 187 3 +342.85 ± 44.76
484449 ncm-dbt-04 567403 500 231 33 236 +145.54 ± 12.85 0 5 48 191 6 +352.8 ± 49.98
484448 ncm-dbt-01 583447 500 221 36 243 +134.95 ± 12.64 0 2 67 175 6 +312.48 ± 41.9
484447 ncm-dbt-03 586816 500 228 42 230 +135.76 ± 12.42 0 2 65 178 5 +318.25 ± 42.59
484446 ncm-dbt-05 602739 500 228 38 234 +138.99 ± 13.67 0 3 65 171 11 +312.48 ± 42.67
484445 ncm-dbt-02 588643 500 231 37 232 +142.25 ± 12.37 0 4 52 190 4 +346.12 ± 48.03
484444 ncm-dbt-04 565823 500 224 50 226 +126.17 ± 13.42 0 8 63 176 3 +290.66 ± 43.37
484443 ncm-dbt-01 584495 500 219 35 246 +134.15 ± 13.24 0 6 59 180 5 +312.48 ± 44.93
484442 ncm-dbt-03 578547 500 234 44 222 +138.99 ± 13.67 0 3 65 171 11 +312.48 ± 42.67
484441 ncm-dbt-05 605568 500 230 35 235 +143.07 ± 12.95 1 1 57 184 7 +342.85 ± 45.71
484440 ncm-dbt-02 589967 500 233 49 218 +134.15 ± 13.8 0 7 59 177 7 +306.84 ± 44.88
484439 ncm-dbt-04 566809 500 218 31 251 +136.56 ± 12.39 0 3 61 182 4 +324.17 ± 44.15
484438 ncm-dbt-01 582945 500 229 40 231 +138.18 ± 13.32 0 3 64 174 9 +315.35 ± 43.03
484437 ncm-dbt-03 580406 500 230 38 232 +140.62 ± 11.36 0 2 55 192 1 +349.43 ± 46.59
484436 ncm-dbt-05 602695 500 235 37 228 +145.54 ± 12.01 0 1 56 187 6 +352.8 ± 46.04
484435 ncm-dbt-02 588515 500 227 37 236 +138.99 ± 13.1 0 2 65 174 9 +318.25 ± 42.59
484434 ncm-dbt-04 566651 500 225 42 233 +133.34 ± 13.08 0 5 62 178 5 +309.64 ± 43.82
484433 ncm-dbt-03 581902 500 224 39 237 +134.95 ± 12.44 0 3 63 180 4 +318.25 ± 43.39
484432 ncm-dbt-01 582819 500 224 35 241 +138.18 ± 12.93 0 2 65 175 8 +318.25 ± 42.59
484431 ncm-dbt-05 607832 500 231 42 227 +138.18 ± 12.73 0 3 61 180 6 +324.17 ± 44.15
484430 ncm-dbt-02 589882 500 233 31 236 +148.85 ± 12.7 0 2 53 186 9 +356.21 ± 47.52
484429 ncm-dbt-04 565587 500 228 38 234 +138.99 ± 12.7 0 2 63 178 7 +324.17 ± 43.32
484428 ncm-dbt-01 581402 500 221 34 245 +136.56 ± 11.55 0 1 63 184 2 +330.23 ± 43.2
484427 ncm-dbt-03 582152 500 214 39 247 +126.96 ± 12.47 0 0 81 163 6 +285.49 ± 37.46
484426 ncm-dbt-05 598568 500 224 33 243 +139.81 ± 12.26 0 3 57 186 4 +336.46 ± 45.77
484425 ncm-dbt-02 591642 500 244 39 217 +151.34 ± 11.92 0 0 53 189 8 +370.41 ± 47.26
484424 ncm-dbt-04 566533 500 234 31 235 +149.68 ± 12.01 0 0 55 187 8 +363.19 ± 46.32
484423 ncm-dbt-01 582987 500 223 37 240 +135.76 ± 12.81 0 4 61 180 5 +318.25 ± 44.18
484422 ncm-dbt-03 581902 500 219 28 253 +139.8 ± 11.62 0 0 63 183 4 +336.45 ± 43.03
484421 ncm-dbt-05 598965 500 233 30 237 +149.68 ± 11.09 0 0 51 195 4 +377.86 ± 48.25
484420 ncm-dbt-02 593369 500 224 40 236 +134.15 ± 12.86 0 4 63 178 5 +312.48 ± 43.44
484419 ncm-dbt-04 565705 500 217 38 245 +130.14 ± 12.59 0 4 66 177 3 +304.07 ± 42.38
484418 ncm-dbt-01 583782 500 225 30 245 +143.07 ± 10.77 0 1 53 196 0 +363.2 ± 47.43
484417 ncm-dbt-03 584832 500 230 36 234 +142.25 ± 12.58 0 0 65 176 9 +330.23 ± 42.3
484416 ncm-dbt-05 616123 500 217 29 254 +137.37 ± 12.56 0 4 58 184 4 +327.18 ± 45.37
484415 ncm-dbt-02 591857 500 231 33 236 +145.54 ± 12.64 0 3 53 187 7 +349.43 ± 47.56
484414 ncm-dbt-04 567244 500 226 30 244 +143.89 ± 13.12 0 3 57 181 9 +336.46 ± 45.77

Commit

Commit ID edb0d9db6731067ec50ce619ff372b463bc4dd5d
Author Joost VandeVondele
Date 2026-09-05 08:02:59 UTC
Stockfish 19 Official release version of Stockfish 19 Bench: 2497913 --- Stockfish 19 Today, we have the pleasure of announcing Stockfish 19, a new major release. As always, you can freely download it at [stockfishchess.org/download][1] and use it as a drop-in replacement in the [GUI of your choice][2] to benefit from stronger play and more accurate analysis. Whether you can spare hours or days of CPU time, your help matters for the ongoing development of Stockfish. Find out how you can contribute at [stockfishchess.org/get-involved][3]. Join our [Discord server][4] to get in touch with the community of developers and users of the project! Quality of Chess Play In tests against Stockfish 18, this new release brings an Elo gain of [up to 44 points][5], and wins [more than three times as many game pairs][6] as it loses. Stockfish continues to set the standard for engine strength. Against the strongest competition, it consistently secures the top spot in engine championships, continuing to [dominate the field][7]. Update Highlights Universal Binaries We have transitioned to universal binaries for our releases, simplifying the download process. These universal binaries automatically detect the features of your CPU and run the optimal code, eliminating the need to manually choose between AVX2, AVX-512, etc. Upgraded NNUE Architecture and Training This release introduces the SFNNv16 network architecture, reducing binary size by removing redundant threat features while increasing strength by introducing new pawn-pair features. The secondary neural network, introduced in Stockfish 16.1, has been retired, enhancing strength in positions where the small net previously underperformed. The training process has been further improved with the introduction of new techniques, such as Quantization-Aware Training (QAT), and further parameter tweaks. These techniques have been applied to hundreds of billions of training positions, all of which have been consistently rescored using a strong [Leela][8] net. Expanded Platform Support We have added native support for RISC-V (RVV) and LoongArch (LSX/LASX), 1GB Linux huge pages, as well as WebAssembly targets. The shared-memory implementation for Linux, macOS, and BSD was also overhauled. Strict Position Validation We have implemented stricter validation for board positions, FEN strings, and UCI commands. The engine will now output an `info string CRITICAL ERROR` followed by the exact command and the reason it failed, and then immediately terminate the process. A good GUI will ensure you never encounter these errors. Thank You The Stockfish project builds on a thriving community of enthusiasts (thanks to everybody!) who contribute their expertise, time, and resources to build a free and open-source chess engine that is robust, widely available, and very strong. We would like to express our gratitude for the 16.4k stars that light up our GitHub project. Thank you for your support and encouragement – your recognition means a lot to us. Programmers can contribute to the project either directly to [Stockfish][9] (C++), to [Fishtest][10] (HTML, CSS, JavaScript, and Python), to our trainer [nnue-pytorch][11] (C++ and Python), or to our [website][12] (HTML, CSS/SCSS, and JavaScript). The Stockfish team [1]: https://stockfishchess.org/download [2]: https://official-stockfish.github.io/docs/stockfish-wiki/Download-and-usage.html#download-a-chess-gui [3]: https://stockfishchess.org/get-involved/ [4]: https://discord.gg/GWDRS3kU6R [5]: https://tests.stockfishchess.org/tests/view/6a85df4c5b1b38ebda864ccd [6]: https://tests.stockfishchess.org/tests/view/6a85df595b1b38ebda864ccf [7]: https://en.wikipedia.org/wiki/Stockfish_(chess)#Competition_results [8]: https://lczero.org/ [9]: https://github.com/official-stockfish/Stockfish [10]: https://github.com/official-stockfish/fishtest [11]: https://github.com/official-stockfish/nnue-pytorch [12]: https://github.com/official-stockfish/stockfish-web
Copyright 2011–2026 Next Chess Move LLC