Stockfish latest official version download:
https://stockfishchess.org/download/
Stockfish beta releases download (only Windows and Linux):
https://abrok.eu/stockfish/
Stockfish Download.
Forum rules
Any post on the Stockfish download MUST include a direct link to download the new executable - MANDATORY.
Any post on the Stockfish download MUST include a direct link to download the new executable - MANDATORY.
-
massimilianogoi
- Site Admin
- Posts: 369
- Joined: Thu Aug 04, 2022 1:42 pm
- Has thanked: 569 times
- Been thanked: 608 times
- Contact:
-
Terminator
- Posts: 7
- Joined: Thu Mar 09, 2023 8:31 am
- Has thanked: 1 time
- Been thanked: 23 times
Re: Stockfish Download.
Author: Michael Chaly
Date: Sat May 20 10:19:03 2023 +0200
Timestamp: 1684570743
Small simplification in low depth pruning
Uncap low depth pruning lmr depth.
It's anyway capped for most cases apart from futility pruning for captures - removes one std::min call.
Passed STC:
https://tests.stockfishchess.org/tests/ ... b2e64225a1
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 184064 W: 49039 L: 48982 D: 86043 Elo +0.11
Ptnml(0-2): 462, 20353, 50349, 20402, 466
Passed LTC:
https://tests.stockfishchess.org/tests/ ... b2e6423335
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 83886 W: 22613 L: 22465 D: 38808 Elo +0.61
Ptnml(0-2): 31, 8090, 25546, 8252, 24
closes https://github.com/official-stockfish/S ... /pull/4566
bench 3201883
see source
https://abrok.eu/stockfish/
Date: Sat May 20 10:19:03 2023 +0200
Timestamp: 1684570743
Small simplification in low depth pruning
Uncap low depth pruning lmr depth.
It's anyway capped for most cases apart from futility pruning for captures - removes one std::min call.
Passed STC:
https://tests.stockfishchess.org/tests/ ... b2e64225a1
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 184064 W: 49039 L: 48982 D: 86043 Elo +0.11
Ptnml(0-2): 462, 20353, 50349, 20402, 466
Passed LTC:
https://tests.stockfishchess.org/tests/ ... b2e6423335
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 83886 W: 22613 L: 22465 D: 38808 Elo +0.61
Ptnml(0-2): 31, 8090, 25546, 8252, 24
closes https://github.com/official-stockfish/S ... /pull/4566
bench 3201883
see source
https://abrok.eu/stockfish/
-
APOCALYPSE
- Posts: 133
- Joined: Fri Oct 14, 2022 6:50 am
- Has thanked: 387 times
- Been thanked: 247 times
- Contact:
Re: Stockfish Download.
Author: cj5716
Date: Thu May 25 20:49:11 2023 +0200
Timestamp: 1685040551
Remove ss->ttHit condition where ttValue != VALUE_NONE
Simplification is done at 3 separate places in the code.
Thanks to peregrineshahin for helping me find 2 of such places.
(See original PR #4584)
Passed non-regression test
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 120256 W: 32204 L: 32085 D: 55967 Elo +0.34
Ptnml(0-2): 292, 12473, 34483, 12584, 296
https://tests.stockfishchess.org/tests/ ... fd984325e3
closes https://github.com/official-stockfish/S ... /pull/4587
No functional change
https://abrok.eu/stockfish/
Date: Thu May 25 20:49:11 2023 +0200
Timestamp: 1685040551
Remove ss->ttHit condition where ttValue != VALUE_NONE
Simplification is done at 3 separate places in the code.
Thanks to peregrineshahin for helping me find 2 of such places.
(See original PR #4584)
Passed non-regression test
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 120256 W: 32204 L: 32085 D: 55967 Elo +0.34
Ptnml(0-2): 292, 12473, 34483, 12584, 296
https://tests.stockfishchess.org/tests/ ... fd984325e3
closes https://github.com/official-stockfish/S ... /pull/4587
No functional change
https://abrok.eu/stockfish/
-
APOCALYPSE
- Posts: 133
- Joined: Fri Oct 14, 2022 6:50 am
- Has thanked: 387 times
- Been thanked: 247 times
- Contact:
Re: Stockfish Download.
Author: windfishballad
Date: Sun May 28 20:05:50 2023 +0200
Timestamp: 1685297150
Removed quadratic term in optimism
Remove term which is quadratic in optimism in the eval.
Simplifies and should also remove the bias towards side to move making the eval better for analysis.
STC: https://tests.stockfishchess.org/tests/ ... 4352b0bca5
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 154432 W: 41127 L: 41040 D: 72265 Elo +0.20
Ptnml(0-2): 380, 17094, 42190, 17163, 389
LTC: https://tests.stockfishchess.org/tests/ ... cf2fb219ef
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 127926 W: 34474 L: 34369 D: 59083 Elo +0.29
Ptnml(0-2): 43, 12505, 38776, 12582, 57
closes https://github.com/official-stockfish/S ... /pull/4590
Bench: 2541211
Date: Sun May 28 20:05:50 2023 +0200
Timestamp: 1685297150
Removed quadratic term in optimism
Remove term which is quadratic in optimism in the eval.
Simplifies and should also remove the bias towards side to move making the eval better for analysis.
STC: https://tests.stockfishchess.org/tests/ ... 4352b0bca5
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 154432 W: 41127 L: 41040 D: 72265 Elo +0.20
Ptnml(0-2): 380, 17094, 42190, 17163, 389
LTC: https://tests.stockfishchess.org/tests/ ... cf2fb219ef
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 127926 W: 34474 L: 34369 D: 59083 Elo +0.29
Ptnml(0-2): 43, 12505, 38776, 12582, 57
closes https://github.com/official-stockfish/S ... /pull/4590
Bench: 2541211
-
APOCALYPSE
- Posts: 133
- Joined: Fri Oct 14, 2022 6:50 am
- Has thanked: 387 times
- Been thanked: 247 times
- Contact:
Re: Stockfish Download.
Author: Linmiao Xu
Date: Wed May 31 08:51:22 2023 +0200
Timestamp: 1685515882
Update NNUE architecture to SFNNv6 with larger L1 size of 1536
Created by training a new net from scratch with L1 size increased from 1024 to 1536.
Thanks to Vizvezdenec for the idea of exploring larger net sizes after recent
training data improvements.
A new net was first trained with lambda 1.0 and constant LR 8.75e-4. Then a strong net
from a later epoch in the training run was chosen for retraining with start-lambda 1.0
and initial LR 4.375e-4 decaying with gamma 0.995. Retraining was performed a total of
3 times, for this 4-step process:
1. 400 epochs, lambda 1.0 on filtered T77+T79 v6 deduplicated data
2. 800 epochs, end-lambda 0.75 on T60T70wIsRightFarseerT60T74T75T76.binpack
3. 800 epochs, end-lambda 0.75 and early-fen-skipping 28 on the master dataset
4. 800 epochs, end-lambda 0.7 and early-fen-skipping 28 on the master dataset
In the training sequence that reached the new nn-8d69132723e2.nnue net,
the epochs used for the 3x retraining runs were:
1. epoch 379 trained on T77T79-filter-v6-dd.min.binpack
2. epoch 679 trained on T60T70wIsRightFarseerT60T74T75T76.binpack
3. epoch 799 trained on the master dataset
For training from scratch:
python3 easy_train.py \
--experiment-name new-L1-1536-T77T79-filter-v6dd \
--training-dataset /data/T77T79-filter-v6-dd.min.binpack \
--max_epoch 400 \
--lambda 1.0 \
--start-from-engine-test-net False \
--engine-test-branch linrock/Stockfish/L1-1536 \
--nnue-pytorch-branch linrock/Stockfish/misc-fixes-L1-1536 \
--tui False \
--gpus "0," \
--seed $RANDOM
Retraining commands were similar to each other. For the 3rd retraining run:
python3 easy_train.py \
--experiment-name L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-Re3-sameData \
--training-dataset /data/leela96-dfrc99-v2-T60novdecT80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd.binpack \
--early-fen-skipping 28 \
--max_epoch 800 \
--start-lambda 1.0 \
--end-lambda 0.7 \
--lr 4.375e-4 \
--gamma 0.995 \
--start-from-engine-test-net False \
--start-from-model /data/L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-nn-epoch799.nnue \
--engine-test-branch linrock/Stockfish/L1-1536 \
--nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \
--tui False \
--gpus "0," \
--seed $RANDOM
The T77+T79 data used is a subset of the master dataset available at:
https://robotmoon.com/nnue-training-data/
T60T70wIsRightFarseerT60T74T75T76.binpack is available at:
https://drive.google.com/drive/folders/ ... xj4zG4V8gG
Local elo at 25k nodes per move vs. nn-e1fb1ade4432.nnue (L1 size 1024):
nn-epoch759.nnue : 26.9 +/- 1.6
Failed STC
https://tests.stockfishchess.org/tests/ ... e4cfa75f97
LLR: -2.94 (-2.94,2.94) <0.00,2.00>
Total: 13728 W: 3588 L: 3829 D: 6311 Elo -6.10
Ptnml(0-2): 71, 1661, 3610, 1482, 40
Failing LTC
https://tests.stockfishchess.org/tests/ ... 3c4c9f3618
LLR: -1.91 (-2.94,2.94) <0.50,2.50>
Total: 35424 W: 9522 L: 9603 D: 16299 Elo -0.79
Ptnml(0-2): 24, 3579, 10585, 3502, 22
Passed VLTC 180+1.8
https://tests.stockfishchess.org/tests/ ... 3c4c9f3638
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 47616 W: 13174 L: 12863 D: 21579 Elo +2.27
Ptnml(0-2): 13, 4261, 14952, 4566, 16
Passed VLTC SMP 60+0.6 th 8
https://tests.stockfishchess.org/tests/ ... e4cfa761e5
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 19942 W: 5694 L: 5451 D: 8797 Elo +4.23
Ptnml(0-2): 6, 1504, 6707, 1749, 5
closes https://github.com/official-stockfish/S ... /pull/4593
bench 2222567
Date: Wed May 31 08:51:22 2023 +0200
Timestamp: 1685515882
Update NNUE architecture to SFNNv6 with larger L1 size of 1536
Created by training a new net from scratch with L1 size increased from 1024 to 1536.
Thanks to Vizvezdenec for the idea of exploring larger net sizes after recent
training data improvements.
A new net was first trained with lambda 1.0 and constant LR 8.75e-4. Then a strong net
from a later epoch in the training run was chosen for retraining with start-lambda 1.0
and initial LR 4.375e-4 decaying with gamma 0.995. Retraining was performed a total of
3 times, for this 4-step process:
1. 400 epochs, lambda 1.0 on filtered T77+T79 v6 deduplicated data
2. 800 epochs, end-lambda 0.75 on T60T70wIsRightFarseerT60T74T75T76.binpack
3. 800 epochs, end-lambda 0.75 and early-fen-skipping 28 on the master dataset
4. 800 epochs, end-lambda 0.7 and early-fen-skipping 28 on the master dataset
In the training sequence that reached the new nn-8d69132723e2.nnue net,
the epochs used for the 3x retraining runs were:
1. epoch 379 trained on T77T79-filter-v6-dd.min.binpack
2. epoch 679 trained on T60T70wIsRightFarseerT60T74T75T76.binpack
3. epoch 799 trained on the master dataset
For training from scratch:
python3 easy_train.py \
--experiment-name new-L1-1536-T77T79-filter-v6dd \
--training-dataset /data/T77T79-filter-v6-dd.min.binpack \
--max_epoch 400 \
--lambda 1.0 \
--start-from-engine-test-net False \
--engine-test-branch linrock/Stockfish/L1-1536 \
--nnue-pytorch-branch linrock/Stockfish/misc-fixes-L1-1536 \
--tui False \
--gpus "0," \
--seed $RANDOM
Retraining commands were similar to each other. For the 3rd retraining run:
python3 easy_train.py \
--experiment-name L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-Re3-sameData \
--training-dataset /data/leela96-dfrc99-v2-T60novdecT80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd.binpack \
--early-fen-skipping 28 \
--max_epoch 800 \
--start-lambda 1.0 \
--end-lambda 0.7 \
--lr 4.375e-4 \
--gamma 0.995 \
--start-from-engine-test-net False \
--start-from-model /data/L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-nn-epoch799.nnue \
--engine-test-branch linrock/Stockfish/L1-1536 \
--nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \
--tui False \
--gpus "0," \
--seed $RANDOM
The T77+T79 data used is a subset of the master dataset available at:
https://robotmoon.com/nnue-training-data/
T60T70wIsRightFarseerT60T74T75T76.binpack is available at:
https://drive.google.com/drive/folders/ ... xj4zG4V8gG
Local elo at 25k nodes per move vs. nn-e1fb1ade4432.nnue (L1 size 1024):
nn-epoch759.nnue : 26.9 +/- 1.6
Failed STC
https://tests.stockfishchess.org/tests/ ... e4cfa75f97
LLR: -2.94 (-2.94,2.94) <0.00,2.00>
Total: 13728 W: 3588 L: 3829 D: 6311 Elo -6.10
Ptnml(0-2): 71, 1661, 3610, 1482, 40
Failing LTC
https://tests.stockfishchess.org/tests/ ... 3c4c9f3618
LLR: -1.91 (-2.94,2.94) <0.50,2.50>
Total: 35424 W: 9522 L: 9603 D: 16299 Elo -0.79
Ptnml(0-2): 24, 3579, 10585, 3502, 22
Passed VLTC 180+1.8
https://tests.stockfishchess.org/tests/ ... 3c4c9f3638
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 47616 W: 13174 L: 12863 D: 21579 Elo +2.27
Ptnml(0-2): 13, 4261, 14952, 4566, 16
Passed VLTC SMP 60+0.6 th 8
https://tests.stockfishchess.org/tests/ ... e4cfa761e5
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 19942 W: 5694 L: 5451 D: 8797 Elo +4.23
Ptnml(0-2): 6, 1504, 6707, 1749, 5
closes https://github.com/official-stockfish/S ... /pull/4593
bench 2222567
-
APOCALYPSE
- Posts: 133
- Joined: Fri Oct 14, 2022 6:50 am
- Has thanked: 387 times
- Been thanked: 247 times
- Contact:
Re: Stockfish Download.
Author: Linmiao Xu
Date: Wed May 31 08:54:38 2023 +0200
Timestamp: 1685516078
Simplify nnue eval complexity calculation
Remove a multiplier when blending nnue complexity with semi-classical complexity.
Passed non-regression STC:
https://tests.stockfishchess.org/tests/ ... e4cfa75839
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 124768 W: 33180 L: 33060 D: 58528 Elo +0.33
Ptnml(0-2): 314, 13797, 34030, 13941, 302
Passed non-regression LTC:
https://tests.stockfishchess.org/tests/ ... e4cfa768f4
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 108180 W: 29008 L: 28884 D: 50288 Elo +0.40
Ptnml(0-2): 29, 10420, 33075, 10530, 36
closes https://github.com/official-stockfish/S ... /pull/4592
bench 2316827
Date: Wed May 31 08:54:38 2023 +0200
Timestamp: 1685516078
Simplify nnue eval complexity calculation
Remove a multiplier when blending nnue complexity with semi-classical complexity.
Passed non-regression STC:
https://tests.stockfishchess.org/tests/ ... e4cfa75839
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 124768 W: 33180 L: 33060 D: 58528 Elo +0.33
Ptnml(0-2): 314, 13797, 34030, 13941, 302
Passed non-regression LTC:
https://tests.stockfishchess.org/tests/ ... e4cfa768f4
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 108180 W: 29008 L: 28884 D: 50288 Elo +0.40
Ptnml(0-2): 29, 10420, 33075, 10530, 36
closes https://github.com/official-stockfish/S ... /pull/4592
bench 2316827
-
APOCALYPSE
- Posts: 133
- Joined: Fri Oct 14, 2022 6:50 am
- Has thanked: 387 times
- Been thanked: 247 times
- Contact:
Re: Stockfish Download.
Author: Michael Chaly
Date: Wed May 31 09:06:30 2023 +0200
Timestamp: 1685516790
Small simplification for probcut in check
Remove depth condition from there as not longer needed.
Passed STC:
https://tests.stockfishchess.org/tests/ ... e4cfa753e6
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 254336 W: 67830 L: 67847 D: 118659 Elo -0.02
Ptnml(0-2): 580, 28181, 69697, 28096, 614
Passed LTC:
https://tests.stockfishchess.org/tests/ ... 3c4c9f3af7
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 80706 W: 22048 L: 21898 D: 36760 Elo +0.65
Ptnml(0-2): 28, 7721, 24712, 7857, 35
closes https://github.com/official-stockfish/S ... /pull/4594
bench 2381945
Date: Wed May 31 09:06:30 2023 +0200
Timestamp: 1685516790
Small simplification for probcut in check
Remove depth condition from there as not longer needed.
Passed STC:
https://tests.stockfishchess.org/tests/ ... e4cfa753e6
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 254336 W: 67830 L: 67847 D: 118659 Elo -0.02
Ptnml(0-2): 580, 28181, 69697, 28096, 614
Passed LTC:
https://tests.stockfishchess.org/tests/ ... 3c4c9f3af7
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 80706 W: 22048 L: 21898 D: 36760 Elo +0.65
Ptnml(0-2): 28, 7721, 24712, 7857, 35
closes https://github.com/official-stockfish/S ... /pull/4594
bench 2381945
-
APOCALYPSE
- Posts: 133
- Joined: Fri Oct 14, 2022 6:50 am
- Has thanked: 387 times
- Been thanked: 247 times
- Contact:
Re: Stockfish Download.
Author: Muzhen Gaming
Date: Sun Jun 4 22:54:13 2023 +0200
Timestamp: 1685912053
Search tuning at very long time control with new net
The most significant change would be the singularBeta formula.
It was first tested by cj5716 (see https://tests.stockfishchess.org/tests/ ... e4cfa74ec7),
and I took much inspiration from that idea.
LTC (fixed games): https://tests.stockfishchess.org/tests/ ... 8e1d990b12
Elo: 0.61 ± 1.2 (95%) LOS: 83.4%
Total: 60000 W: 16278 L: 16172 D: 27550 Elo +0.61
Ptnml(0-2): 16, 5845, 18179, 5937, 23
nElo: 1.38 ± 2.8 (95%) PairsRatio: 1.02
VLTC 180+1.8: https://tests.stockfishchess.org/tests/ ... 8e1d990b2b
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 33224 W: 9261 L: 8984 D: 14979 Elo +2.90
Ptnml(0-2): 5, 2809, 10710, 3080, 8
SMP VLTC 8-thread: https://tests.stockfishchess.org/tests/ ... 8e1d992425
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 61398 W: 17386 L: 17081 D: 26931 Elo +1.73
Ptnml(0-2): 7, 4571, 21232, 4888, 1
closes https://github.com/official-stockfish/S ... /pull/4603
Bench: 2805878
Date: Sun Jun 4 22:54:13 2023 +0200
Timestamp: 1685912053
Search tuning at very long time control with new net
The most significant change would be the singularBeta formula.
It was first tested by cj5716 (see https://tests.stockfishchess.org/tests/ ... e4cfa74ec7),
and I took much inspiration from that idea.
LTC (fixed games): https://tests.stockfishchess.org/tests/ ... 8e1d990b12
Elo: 0.61 ± 1.2 (95%) LOS: 83.4%
Total: 60000 W: 16278 L: 16172 D: 27550 Elo +0.61
Ptnml(0-2): 16, 5845, 18179, 5937, 23
nElo: 1.38 ± 2.8 (95%) PairsRatio: 1.02
VLTC 180+1.8: https://tests.stockfishchess.org/tests/ ... 8e1d990b2b
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 33224 W: 9261 L: 8984 D: 14979 Elo +2.90
Ptnml(0-2): 5, 2809, 10710, 3080, 8
SMP VLTC 8-thread: https://tests.stockfishchess.org/tests/ ... 8e1d992425
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 61398 W: 17386 L: 17081 D: 26931 Elo +1.73
Ptnml(0-2): 7, 4571, 21232, 4888, 1
closes https://github.com/official-stockfish/S ... /pull/4603
Bench: 2805878
-
APOCALYPSE
- Posts: 133
- Joined: Fri Oct 14, 2022 6:50 am
- Has thanked: 387 times
- Been thanked: 247 times
- Contact:
Re: Stockfish Download.
Author: Linmiao Xu
Date: Sun Jun 4 22:56:44 2023 +0200
Timestamp: 1685912204
Simplify blending nnue complexity with optimism
Passed non-regression STC:
https://tests.stockfishchess.org/tests/ ... 8e1d98f21c
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 241248 W: 64058 L: 64063 D: 113127 Elo -0.01
Ptnml(0-2): 644, 26679, 65960, 26720, 621
Passed non-regression LTC:
https://tests.stockfishchess.org/tests/ ... 8e1d9928b2
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 24336 W: 6658 L: 6451 D: 11227 Elo +2.96
Ptnml(0-2): 8, 2316, 7312, 2525, 7
closes https://github.com/official-stockfish/S ... /pull/4602
bench 2425813
Date: Sun Jun 4 22:56:44 2023 +0200
Timestamp: 1685912204
Simplify blending nnue complexity with optimism
Passed non-regression STC:
https://tests.stockfishchess.org/tests/ ... 8e1d98f21c
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 241248 W: 64058 L: 64063 D: 113127 Elo -0.01
Ptnml(0-2): 644, 26679, 65960, 26720, 621
Passed non-regression LTC:
https://tests.stockfishchess.org/tests/ ... 8e1d9928b2
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 24336 W: 6658 L: 6451 D: 11227 Elo +2.96
Ptnml(0-2): 8, 2316, 7312, 2525, 7
closes https://github.com/official-stockfish/S ... /pull/4602
bench 2425813