Dev Builds » 20260131-1146

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 06:46:48 582864 4008 1724 370 1914 +122.17 ± 4.51 1 27 620 1329 27 +277.1 ± 13.62
ncm-dbt-02 06:45:05 586365 4016 1762 377 1877 +124.94 ± 4.54 0 29 599 1346 34 +283.46 ± 13.87
ncm-dbt-03 06:46:04 586030 4000 1727 383 1890 +121.46 ± 4.52 0 40 593 1350 17 +277.62 ± 13.97
ncm-dbt-04 06:43:41 567097 3994 1724 401 1869 +119.6 ± 4.58 0 29 650 1284 34 +266.65 ± 13.28
ncm-dbt-05 06:44:47 583070 3982 1713 369 1900 +122.05 ± 4.58 0 38 596 1332 25 +276.98 ± 13.93
20000 8650 1900 9450 +122.04 ± 2.03 1 163 3058 6641 137 +276.31 ± 6.14

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
452864 ncm-dbt-01 582402 8 4 1 3 +136.8 ± 89.09 0 0 1 3 0 +337.69 ± 541.44
452863 ncm-dbt-02 587537 16 8 3 5 +112.26 ± 65.75 0 0 3 5 0 +254.61 ± 287.37
452862 ncm-dbt-05 582652 482 198 55 229 +106.27 ± 13.53 0 7 86 146 2 +232.83 ± 36.86
452861 ncm-dbt-04 565469 494 209 48 237 +117.52 ± 12.92 0 3 84 156 4 +260.86 ± 37.09
452860 ncm-dbt-03 587409 500 216 48 236 +121.45 ± 13.14 0 7 70 171 2 +277.93 ± 41.14
452859 ncm-dbt-01 583740 500 210 40 250 +123.02 ± 12.37 0 3 76 169 2 +282.94 ± 39.21
452858 ncm-dbt-02 585674 500 222 54 224 +121.45 ± 13.14 0 6 73 168 3 +275.45 ± 40.24
452857 ncm-dbt-05 578013 500 210 39 251 +123.81 ± 12.16 0 2 77 169 2 +285.49 ± 38.83
452856 ncm-dbt-04 567997 500 214 52 234 +116.77 ± 13.19 0 5 82 159 4 +258.75 ± 37.76
452855 ncm-dbt-03 586266 500 214 54 232 +115.23 ± 12.67 0 6 78 166 0 +263.42 ± 38.85
452854 ncm-dbt-01 581361 500 212 50 238 +116.77 ± 12.65 0 5 79 165 1 +265.78 ± 38.54
452853 ncm-dbt-02 586350 500 214 44 242 +123.02 ± 12.74 0 5 72 171 2 +282.94 ± 40.5
452852 ncm-dbt-05 580655 500 213 55 232 +113.68 ± 13.21 0 6 83 158 3 +251.89 ± 37.57
452851 ncm-dbt-04 567205 500 222 51 227 +123.81 ± 13.28 0 4 77 163 6 +275.45 ± 39.01
452850 ncm-dbt-03 586689 500 210 51 239 +114.45 ± 12.49 0 4 84 161 1 +258.75 ± 37.2
452849 ncm-dbt-01 582277 500 213 53 234 +115.23 ± 13.2 1 3 84 159 3 +258.75 ± 37.2
452848 ncm-dbt-02 586266 500 229 47 224 +132.54 ± 12.91 0 1 74 167 8 +298.62 ± 39.56
452847 ncm-dbt-05 582444 500 222 35 243 +136.56 ± 12.98 0 4 61 179 6 +318.25 ± 44.18
452846 ncm-dbt-04 566888 500 211 47 242 +118.33 ± 13.0 0 3 85 157 5 +261.07 ± 36.86
452845 ncm-dbt-03 585928 500 223 48 229 +126.97 ± 13.41 0 6 68 171 5 +288.06 ± 41.76
452844 ncm-dbt-01 580447 500 214 48 238 +119.89 ± 12.04 0 1 84 163 2 +273.0 ± 36.86
452843 ncm-dbt-02 582027 500 218 47 235 +123.81 ± 11.96 0 1 79 168 2 +285.49 ± 38.15
452842 ncm-dbt-04 565823 500 218 44 238 +126.17 ± 12.1 0 0 80 166 4 +288.06 ± 37.72
452841 ncm-dbt-05 581777 500 231 53 216 +129.35 ± 12.8 0 4 68 174 4 +298.62 ± 41.71
452840 ncm-dbt-03 585717 500 228 42 230 +135.76 ± 12.21 0 3 61 183 3 +324.17 ± 44.15
452839 ncm-dbt-01 583866 500 217 43 240 +126.17 ± 12.87 0 3 75 167 5 +285.49 ± 39.5
452838 ncm-dbt-02 586139 500 210 43 247 +120.67 ± 13.15 0 5 77 164 4 +270.57 ± 39.07
452837 ncm-dbt-05 575924 500 218 46 236 +124.6 ± 12.71 0 5 70 173 2 +288.06 ± 41.11
452836 ncm-dbt-04 567244 500 218 52 230 +119.89 ± 12.79 0 3 82 161 4 +268.17 ± 37.61
452835 ncm-dbt-03 585295 500 211 54 235 +112.91 ± 12.69 0 5 84 160 1 +254.16 ± 37.27
452834 ncm-dbt-02 587325 500 223 39 238 +134.15 ± 12.86 0 4 63 178 5 +312.48 ± 43.44
452833 ncm-dbt-01 584243 500 230 45 225 +134.95 ± 12.84 0 2 68 173 7 +309.64 ± 41.56
452832 ncm-dbt-04 567720 500 216 46 238 +123.02 ± 12.74 0 4 75 168 3 +280.42 ± 39.57
452831 ncm-dbt-05 583824 500 210 35 255 +126.97 ± 12.47 0 4 69 175 2 +295.94 ± 41.39
452830 ncm-dbt-02 587409 500 220 45 235 +126.97 ± 13.04 0 4 72 169 5 +288.06 ± 40.46
452829 ncm-dbt-03 583698 500 212 38 250 +126.17 ± 13.06 0 5 70 171 4 +288.06 ± 41.11
452828 ncm-dbt-01 582318 500 208 43 249 +119.11 ± 13.34 0 6 77 163 4 +265.78 ± 39.12
452827 ncm-dbt-04 568434 500 216 61 223 +111.37 ± 13.56 0 7 85 154 4 +243.0 ± 37.13
452826 ncm-dbt-05 599274 500 211 51 238 +115.22 ± 13.38 0 6 82 158 4 +254.16 ± 37.82
452825 ncm-dbt-02 588558 500 218 55 227 +117.55 ± 13.0 0 3 86 156 5 +258.75 ± 36.62
452824 ncm-dbt-03 587240 500 213 48 239 +119.11 ± 12.43 0 4 78 167 1 +273.0 ± 38.74
452823 ncm-dbt-01 585126 500 216 47 237 +122.24 ± 12.76 0 4 76 167 3 +277.93 ± 39.29

Commit

Commit ID cb3d4ee9b47d0c5aae855b12379378ea1439675c
Author Joost VandeVondele
Date 2026-01-31 11:46:49 UTC
Stockfish 18 Official release version of Stockfish 18 Bench: 2050811 --- Stockfish 18 Today, we have the pleasure of announcing Stockfish 18, 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 help 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 17, this new release brings an Elo gain of up to [46 points][5], and wins [four times as many game pairs][6] as it loses. Quality improved throughout, including in [Fischer Random Chess][7]. Stockfish is stronger than any human, even when running on older or low-end hardware. On the highest-end hardware, where Stockfish can search over [500 million positions per second][8], it continues to [dominate chess engine tournaments][9]. Update highlights Next-Generation Evaluation This release introduces the SFNNv10 network architecture. The network’s input layer has been augmented with 'Threat Inputs' features as part of a massive community effort. These features allow the engine to 'see' which pieces are threatened more naturally, resulting in more accurate evaluations. Hardware and Performance Optimizations A key highlight is the new 'Shared Memory' implementation, which allows different Stockfish processes to share the same memory space for neural network weights. This makes it the most efficient version for cloud analysis and high-concurrency testing. Significant efforts have also been made to utilize hardware more effectively by adapting the code to make use of modern CPU instructions and refining how threads interact during a search. Search Improvements Stockfish 18 features a heavily refined search, utilizing 'Correction History' to dynamically adjust evaluations based on patterns found during the search itself. These and other refinements allow the engine to detect stalemates and evaluate fortresses significantly better than previous versions. A particularly rare issue, involving threefold repetition detection, en passant, and pins, was also fixed. Refactored Training Workflow The training of Stockfish's neural networks has transitioned to an automated and reproducible model. This new framework allows the project to employ standardized recipes to chain complex training stages together. This transition facilitates the training of networks using over 100 billion positions of [Lc0 evaluation data][10]. Thank you In this release in particular, we are deeply grateful to the contributors who shared their research and ideas to help develop the new threat-input network architecture. 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 [14.6k stars][11] 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][12] (C++), to [Fishtest][13] (HTML, CSS, JavaScript, and Python), to our trainer [nnue-pytorch][14] (C++ and Python), or to our [website][15] (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/696a9e15cec152c6220c1d19 [6]: https://tests.stockfishchess.org/tests/view/696a9e4dcec152c6220c1d1b [7]: https://tests.stockfishchess.org/tests/view/696a9e83cec152c6220c1d1d [8]: https://openbenchmarking.org/test/pts/stockfish [9]: https://en.wikipedia.org/wiki/Stockfish_(chess)#Competition_results [10]: https://lczero.org/blog/2021/06/the-importance-of-open-data/ [11]: https://github.com/official-stockfish/Stockfish/stargazers [12]: https://github.com/official-stockfish/Stockfish [13]: https://github.com/official-stockfish/fishtest [14]: https://github.com/official-stockfish/nnue-pytorch [15]: https://github.com/official-stockfish/stockfish-web
Copyright 2011–2026 Next Chess Move LLC