| !! latest version !! Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Taras Vuk
Date: Tue Dec 23 21:42:45 2025 +0100 Timestamp: 1766522565 Incorporate statscore into history bonus Passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 80128 W: 20879 L: 20498 D: 38751 Elo +1.65 Ptnml(0-2): 274, 9318, 20496, 9705, 271 https://tests.stockfishchess.org/tests/view/6945d11f3c8768ca45072218 Passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 134298 W: 34497 L: 33983 D: 65818 Elo +1.33 Ptnml(0-2): 81, 14334, 37812, 14834, 88 https://tests.stockfishchess.org/tests/view/6947bf033c8768ca45072491 closes https://github.com/official-stockfish/Stockfish/pull/6488 Bench: 2325401 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Disservin
Date: Tue Dec 23 21:42:45 2025 +0100 Timestamp: 1766522565 Init threat offsets at compile time Init threat offsets at compile time. Avoid another global init function call. Passed STC Non-Regression: https://tests.stockfishchess.org/tests/view/694971a83c8768ca4507275c LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 43296 W: 11284 L: 11077 D: 20935 Elo +1.66 Ptnml(0-2): 152, 4611, 11924, 4800, 161 closes https://github.com/official-stockfish/Stockfish/pull/6487 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: FauziAkram
Date: Tue Dec 23 21:42:45 2025 +0100 Timestamp: 1766522565 Simplify doDeeperSearch formula Passed STC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 211776 W: 54939 L: 54911 D: 101926 Elo +0.05 Ptnml(0-2): 714, 24971, 54484, 25011, 708 https://tests.stockfishchess.org/tests/view/6938971875b70713ef796b70 Passed LTC: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 216774 W: 55346 L: 55326 D: 106102 Elo +0.03 Ptnml(0-2): 105, 23599, 60980, 23577, 126 https://tests.stockfishchess.org/tests/view/693fc91f46f342e1ec20f9f6 closes https://github.com/official-stockfish/Stockfish/pull/6486 Bench: 3267755 see source |
| Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Michael Chaly
Date: Tue Dec 23 21:42:45 2025 +0100 Timestamp: 1766522565 Less penalty for quiet late moves that didn't beat the best move. This moves since they are late in move ordering probably already have pretty bad stats anyway. Passed STC: https://tests.stockfishchess.org/tests/view/6943bcd546f342e1ec210e25 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 96704 W: 25206 L: 24798 D: 46700 Elo +1.47 Ptnml(0-2): 357, 11244, 24767, 11602, 382 Passed LTC: https://tests.stockfishchess.org/tests/view/6946a8723c8768ca450722f0 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 89814 W: 23193 L: 22770 D: 43851 Elo +1.64 Ptnml(0-2): 53, 9532, 25321, 9941, 60 bench 2717363 closes https://github.com/official-stockfish/Stockfish/pull/6485 Bench: 2791988 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: anematode
Date: Tue Dec 23 21:42:29 2025 +0100 Timestamp: 1766522549 Share correction history between threads We did quite a few tests because this is a pretty involved change with unknown scaling behavior, but results are decent. [STC 10+0.1 1th, non-regression](https://tests.stockfishchess.org/tests/live_elo/6941ce3b46f342e1ec210180) ``` LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 83200 W: 21615 L: 21452 D: 40133 Elo +0.68 Ptnml(0-2): 247, 9064, 22844, 9169, 276 ``` [STC 5+0.05 8th](https://tests.stockfishchess.org/tests/live_elo/693dc38346f342e1ec20f555) ``` LLR: 3.48 (-2.94,2.94) <0.00,2.00> Total: 58536 W: 15067 L: 14688 D: 28781 Elo +2.25 Ptnml(0-2): 87, 6474, 15781, 6825, 101 ``` [LTC 20+0.2 8th](https://tests.stockfishchess.org/tests/live_elo/693f2afb46f342e1ec20f847) ``` LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 27716 W: 7211 L: 6925 D: 13580 Elo +3.59 Ptnml(0-2): 8, 2674, 8207, 2962, 7 ``` [LTC 10+0.1 64th](https://tests.stockfishchess.org/tests/live_elo/694003aa46f342e1ec20fac4): ``` LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 16918 W: 4439 L: 4182 D: 8297 Elo +5.28 Ptnml(0-2): 3, 1493, 5213, 1744, 6 ``` [NUMA test, 5+0.05 256th](https://tests.stockfishchess.org/tests/view/6941ee4e46f342e1ec210203) ``` LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 7124 W: 1910 L: 1678 D: 3536 Elo +11.32 Ptnml(0-2): 0, 560, 2211, 790, 1 ``` [LTC 60+0.6 64th](https://tests.stockfishchess.org/tests/live_elo/6940a85346f342e1ec20fcde): ``` LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 15504 W: 4045 L: 3826 D: 7633 Elo +4.91 Ptnml(0-2): 0, 1002, 5530, 1219, 1 ``` Bonus (courtesy of Viz): The 1 double kill in this last test was master blundering a cool mate in 3: https://lichess.org/jyNZuRl4 Basically the idea here is to share correction history between threads. That way, T1 can use the correction values produced by T2, which already searched positions with that pawn structure etc., so that T1 can search more efficiently. The table size per thread is about the same, so we shouldn't get a large increase in hash collisions; in fact, I'd expect a lower collision rate overall. Although I came up with and implemented the idea independently, [Caissa](https://github.com/Witek902/Caissa) was the first engine to implement corrhist sharing (and corrhist in the first place) – this idea is not completely novel. The table size is rounded to a power of two. In particular, it's `65536 * nextPowerOfTwo(threadCount)`. That way, the indexing operation becomes an AND of the key bits with a mask, rather than something more expensive (e.g., a `mul_hi64`-style approach or a modulo). The updates are racy, like the TT, but because `entry` is hoisted into a register, there's no risk of writing back a value that's out of the designated range `[-D, D]`. Various attempts at rewriting using atomics led to substantial slowdowns, so we begrudgingly ignored the functions in thread sanitizer, but at some point we'd like to make this better. We allocate one shared correction history per NUMA node, because the penalty associated with crossing nodes is substantial – I get a 40% hit with NPS=4 and 256 threads, which is intolerable. With separate tables per NUMA node I get a 6% penalty for nodes per second, which isn't ideal but apparently compensated for. closes https://github.com/official-stockfish/Stockfish/pull/6478 Bench: 2690604 Co-authored-by: Disservin <> see source |
| Windows x64 for Haswell CPUs Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: FauziAkram
Date: Tue Dec 23 21:41:34 2025 +0100 Timestamp: 1766522494 Remove low ply history for check evasions scoring Passed STC: LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 81888 W: 21336 L: 21166 D: 39386 Elo +0.72 Ptnml(0-2): 284, 9438, 21342, 9584, 296 https://tests.stockfishchess.org/tests/view/692ada47b23dfeae38cffce5 Passed LTC: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 107328 W: 27534 L: 27404 D: 52390 Elo +0.42 Ptnml(0-2): 55, 11390, 30659, 11490, 70 https://tests.stockfishchess.org/tests/view/692d7a01b23dfeae38d011ab closes https://github.com/official-stockfish/Stockfish/pull/6467 Bench: 3006182 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: AliceRoselia
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Simplify futility pruning Passed non regression STC: https://tests.stockfishchess.org/tests/view/693e642c46f342e1ec20f68d LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 107968 W: 28080 L: 27937 D: 51951 Elo +0.46 Ptnml(0-2): 381, 12708, 27626, 12925, 344 Passed non regression LTC: https://tests.stockfishchess.org/tests/view/693ff10c46f342e1ec20fa6a LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 334266 W: 85271 L: 85370 D: 163625 Elo -0.10 Ptnml(0-2): 179, 36395, 94086, 36292, 181 closes https://github.com/official-stockfish/Stockfish/pull/6484 Bench: 2987379 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Shawn Xu
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Remove Secondary TT Aging Passed VVLTC w/ STC Bounds: LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 107006 W: 27676 L: 27326 D: 52004 Elo +1.14 Ptnml(0-2): 21, 9505, 34097, 9863, 17 https://tests.stockfishchess.org/tests/view/6939ac5b75b70713ef796f11 Passed VVLTC w/ LTC Bounds: LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 263190 W: 67547 L: 66837 D: 128806 Elo +0.94 Ptnml(0-2): 32, 23939, 82942, 24651, 31 https://tests.stockfishchess.org/tests/view/692165823b03dd3a060e666d closes https://github.com/official-stockfish/Stockfish/pull/6480 Bench: 2800411 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: sscg13
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Represent threat weights directly as i8 LEB128 adds no additional compression and adds extra complexity to the code currently. closes https://github.com/official-stockfish/Stockfish/pull/6479 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Daniel Monroe
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Remove rootDepth condition in newDepth clamping Passed simplification STC LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 132256 W: 34462 L: 34347 D: 63447 Elo +0.30 Ptnml(0-2): 470, 15625, 33833, 15720, 480 https://tests.stockfishchess.org/tests/view/69325fe0a24a6df719fcca16 Passed simplification LTC LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 128220 W: 32503 L: 32392 D: 63325 Elo +0.30 Ptnml(0-2): 94, 13900, 35982, 14069, 65 https://tests.stockfishchess.org/tests/view/6934c2b3a24a6df719fcdf1e closes https://github.com/official-stockfish/Stockfish/pull/6472 Bench: 2926903 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: ppigazzini
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 chore(ci): bump runner to macos-15 closes https://github.com/official-stockfish/Stockfish/pull/6475 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Pieter te Brake
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Removed redundant board updates Contrary to what the comment says, `remove_piece` does in fact set the relevant `board` elements to `NO_PIECE`. closes https://github.com/official-stockfish/Stockfish/pull/6471 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Timothy Herchen
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Tweak nnue_accumulator indexing ``` LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 92736 W: 24149 L: 23764 D: 44823 Elo +1.44 Ptnml(0-2): 280, 10056, 25334, 10395, 303 ``` The use of `IndexType` in the loops is suboptimal because it requires truncation to 32 bits, and thereby defeats some optimizations. Using `size_t` for the loop body works nicely, and a signed index into the index lists allows the compiler to assume the case `added.size() == UINT_MAX`, which would be an infinite loop, to not happen. Passed STC https://tests.stockfishchess.org/tests/live_elo/692fd98ab23dfeae38d01d98 closes https://github.com/official-stockfish/Stockfish/pull/6466 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: mstembera
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Fix one error and all warnings on MSVC 2026 The error is "C1001: Internal compiler error." in uci.cpp on line 370 of master. For some reason the compiler can't handle the std::size(hashfullAges) inside the lambda. Older MSVC versions had no problem. Most of the warnings are due to implicit type conversions "conversion from type A to type B, possible loss of data" many of which have been present for a while. closes https://github.com/official-stockfish/Stockfish/pull/6464 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Daniel Monroe
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Remove non-functional term in isShuffling closes https://github.com/official-stockfish/Stockfish/pull/6462 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Timothy Herchen
Date: Sun Dec 21 15:43:32 2025 +0100 Timestamp: 1766328212 Small threat-related cleanups Remove a couple unused things, mark `noRaysContaining` as `[[maybe_unused]]` (suggested by Viz) to silence a warning on GCC 10, update a comment, and replace inline constants closes https://github.com/official-stockfish/Stockfish/pull/6460 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: FauziAkram
Date: Sun Dec 21 15:43:25 2025 +0100 Timestamp: 1766328205 Simplify piece threat calculation Passed STC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 105984 W: 27206 L: 27067 D: 51711 Elo +0.46 Ptnml(0-2): 260, 11556, 29245, 11647, 284 https://tests.stockfishchess.org/tests/view/6914798e7ca87818523317cf Passed LTC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 53028 W: 13635 L: 13456 D: 25937 Elo +1.17 Ptnml(0-2): 28, 5184, 15908, 5369, 25 https://tests.stockfishchess.org/tests/view/6918c5fc7ca8781852332312 closes https://github.com/official-stockfish/Stockfish/pull/6459 No functional change see source |
| Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: FauziAkram
Date: Sun Dec 21 15:22:06 2025 +0100 Timestamp: 1766326926 Fix Typo closes https://github.com/official-stockfish/Stockfish/pull/6436 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Timothy Herchen
Date: Wed Dec 3 12:32:29 2025 +0100 Timestamp: 1764761549 fix missing condition Fixes a bug in https://github.com/official-stockfish/Stockfish/pull/6453 https://github.com/official-stockfish/Stockfish/commit/abd835dcbc3a28481224f6253b00b7420d062513 The modifications to the DirtyThreats bitboards should only happen if PutPiece is true. This somehow didn't affect bench at the default parameters. Reference AVX2: ./stockfish.killdeer-fix.avx2 bench 64 1 23 Nodes searched : 178140156 Nodes/second : 1503152 before patch: ./stockfish.master.avx512icl bench 64 1 23 Nodes searched : 218349728 Nodes/second : 1743450 after patch: ./stockfish.killdeer-fix.avx512icl bench 64 1 23 Nodes searched : 178140156 Nodes/second : 1727520 passed STC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 39328 W: 10293 L: 10080 D: 18955 Elo +1.88 Ptnml(0-2): 113, 4306, 10629, 4487, 129 https://tests.stockfishchess.org/tests/view/692fb2d8b23dfeae38d01c81 closes https://github.com/official-stockfish/Stockfish/pull/6463 Bench: 2912398 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Daniel Monroe
Date: Mon Dec 1 17:35:34 2025 +0100 Timestamp: 1764606934 Move hindsight reductions above cutoffs Passed STC LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 52640 W: 13701 L: 13361 D: 25578 Elo +2.24 Ptnml(0-2): 168, 6143, 13356, 6487, 166 https://tests.stockfishchess.org/tests/view/6918dc407ca8781852332339 Passed LTC LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 207690 W: 53187 L: 52520 D: 101983 Elo +1.12 Ptnml(0-2): 93, 22515, 57994, 23118, 125 https://tests.stockfishchess.org/tests/view/6919dd307ca87818523324c7 closes https://github.com/official-stockfish/Stockfish/pull/6448 Bench: 2912398 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Timothy Herchen
Date: Mon Dec 1 17:26:50 2025 +0100 Timestamp: 1764606410 Improve update_piece_threats passed on avx512ICL: LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 30240 W: 8026 L: 7726 D: 14488 Elo +3.45 Ptnml(0-2): 95, 3235, 8171, 3513, 106 https://tests.stockfishchess.org/tests/view/69281d9ab23dfeae38cfeeb8 passed on generic architectures: LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 73184 W: 19183 L: 18821 D: 35180 Elo +1.72 Ptnml(0-2): 258, 7988, 19744, 8338, 264 https://tests.stockfishchess.org/tests/view/6928ba11b23dfeae38cff276 subsequent cleanups tested as: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 72480 W: 18678 L: 18502 D: 35300 Elo +0.84 Ptnml(0-2): 242, 7925, 19718, 8125, 230 https://tests.stockfishchess.org/tests/view/692a26adb23dfeae38cff566 We add an argument noRaysContaining, which skips all discoveries which contain all bits in the argument; if the argument is from | to, then this will eliminate the discovery. Separately, on AVX512ICL we can speed up the computation of DirtyThreats by moving from a pop_lsb loop to a vector extraction with vpcompressb. See PR for details. closes https://github.com/official-stockfish/Stockfish/pull/6453 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Joost VandeVondele
Date: Sun Nov 30 21:58:35 2025 +0100 Timestamp: 1764536315 Update main network to nn-2962dca31855.nnue trained with https://github.com/vondele/nettest/blob/dd921672bd4ad8eb09fa45248078450857e81884/threats.yaml on top off and tested against https://github.com/official-stockfish/Stockfish/pull/6452 passed STC LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 130720 W: 34028 L: 33570 D: 63122 Elo +1.22 Ptnml(0-2): 435, 15348, 33384, 15710, 483 https://tests.stockfishchess.org/tests/view/69294539b23dfeae38cff3ad passed LTC LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 51144 W: 13140 L: 12794 D: 25210 Elo +2.35 Ptnml(0-2): 38, 5370, 14408, 5720, 36 https://tests.stockfishchess.org/tests/view/692a9c37b23dfeae38cffa4f closes https://github.com/official-stockfish/Stockfish/pull/6457 Bench: 2823033 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: KazApps
Date: Sun Nov 30 21:58:35 2025 +0100 Timestamp: 1764536315 Update AUTHORS (KazApps) closes https://github.com/official-stockfish/Stockfish/pull/6454 No functional change see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: Joost VandeVondele
Date: Sun Nov 30 21:58:35 2025 +0100 Timestamp: 1764536315 Update main network to nn-87a9d7857d88.nnue trained with https://github.com/vondele/nettest/blob/842d95177f882c0e9b5262247c38d8fcb3e0f3db/threats.yaml passed STC: LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 114880 W: 30291 L: 29851 D: 54738 Elo +1.33 Ptnml(0-2): 499, 13547, 28947, 13909, 538 https://tests.stockfishchess.org/tests/view/6923ec4bba083df4ca63dd39 passed LTC: LLR: 2.97 (-2.94,2.94) <0.50,2.50> Total: 113268 W: 29115 L: 28634 D: 55519 Elo +1.48 Ptnml(0-2): 114, 12295, 31340, 12766, 119 https://tests.stockfishchess.org/tests/view/6925cd01b23dfeae38cfe134 closes https://github.com/official-stockfish/Stockfish/pull/6452 Bench: 3028457 see source |
| Windows x64 for Haswell CPUs Windows x64 for modern computers + AVX2 Windows x64 for modern computers Windows x64 + SSSE3 Windows x64 Linux x64 for Haswell CPUs Linux x64 for modern computers + AVX2 Linux x64 for modern computers Linux x64 + SSSE3 Linux x64 | Author: FauziAkram
Date: Sun Nov 30 21:58:35 2025 +0100 Timestamp: 1764536315 Simplify the highBestMoveEffort formula in Time management Passed STC: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 22272 W: 5885 L: 5655 D: 10732 Elo +3.59 Ptnml(0-2): 76, 2329, 6108, 2535, 88 https://tests.stockfishchess.org/tests/view/69244d07ba083df4ca63e02b Passed LTC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 48690 W: 12405 L: 12221 D: 24064 Elo +1.31 Ptnml(0-2): 29, 4755, 14597, 4931, 33 https://tests.stockfishchess.org/tests/view/6924de9aba083df4ca63e327 closes https://github.com/official-stockfish/Stockfish/pull/6451 No functional change see source |