FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Active : 11 Machines / 238 Threads / 226.16 MNPS
Priority 0
Caissa Witek
see-prune-capture-history
diff10.0+0.10
ELO    1.15 +- 1.23 (95%)
LLR    1.64 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 81426 W: 19484 L: 19215 D: 42727
PENTA  [287, 9604, 20677, 9843, 302]
Caissa Witek
tm-clock-disadvantage
diff60.0+0.60
ELO    6.65 +- 8.46 (95%)
LLR    0.47 (-2.94, 2.94) [-0.50, 2.50]
GAMES  N: 1464 W: 372 L: 344 D: 748
PENTA  [2, 144, 411, 174, 1]
PlentyChess Yoshie2000
multicut-counter
diff8.0+0.08
ELO    1.13 +- 6.42 (95%)
LLR    0.06 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 2772 W: 663 L: 654 D: 1455
PENTA  [2, 327, 720, 334, 3]
Quanticade DarkNeutrino
net62
Simply 1024L1
smp diff10.0+0.10
ELO    2.93 +- 15.83 (95%)
LLR    0.05 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 474 W: 115 L: 111 D: 248
PENTA  [2, 52, 123, 60, 0]
Caissa Witek
razoring-no-depth-limit
diff8.0+0.08
ELO    -0.87 +- 1.32 (95%)
LLR    -0.62 (-2.94, 2.94) [-2.50, 0.00]
GAMES  N: 73064 W: 17433 L: 17616 D: 38015
PENTA  [332, 8809, 18403, 8686, 302]
Priority -1
Integral Fury
[Reckless] main
diff60.0+0.60
ELO    2.23 +- 27.04 (95%)
GAMES  N: 156/10000 W: 39 L: 38 D: 79
PENTA  [0, 18, 41, 19, 0]
Quanticade DarkNeutrino
ldse-correction
search.c: Apply correction to ldse extensions
diff60.0+0.60
ELO    -0.64 +- 4.04 (95%)
LLR    -0.46 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6474 W: 1483 L: 1495 D: 3496
PENTA  [1, 738, 1772, 724, 2]
Caissa Witek
eval-ml-12-branch-150B-permuted
diff10.0+0.10
ELO    0.25 +- 0.79 (95%)
LLR    -1.68 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 197400 W: 46606 L: 46463 D: 104331
PENTA  [651, 23735, 49849, 23750, 715]
Finished
PlentyChess Yoshie2000
multicut-killer
diff8.0+0.08
ELO    -2.05 +- 2.37 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 20298 W: 4869 L: 4989 D: 10440
PENTA  [44, 2397, 5368, 2315, 25]
Quanticade DarkNeutrino
net62
net62
diff10.0+0.10
ELO    -9.65 +- 10.59 (95%)
LLR    -0.57 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 1152 W: 260 L: 292 D: 600
PENTA  [6, 155, 283, 129, 3]
Quanticade DarkNeutrino
net62
net62
diffN=5000
ELO    20.71 +- 7.23 (95%)
LLR    3.22 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 4956 W: 1815 L: 1520 D: 1621
PENTA  [169, 482, 962, 615, 250]
PlentyChess Yoshie2000
contcorr-2
diff8.0+0.08
ELO    -2.67 +- 2.61 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 16644 W: 3950 L: 4078 D: 8616
PENTA  [25, 2001, 4403, 1863, 30]
PlentyChess Yoshie2000
real-contcorr-3
crash diff40.0+0.40
ELO    0.52 +- 1.39 (95%)
LLR    -0.16 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 53764 W: 13017 L: 12936 D: 27811
PENTA  [4, 5987, 14821, 6064, 6]
Integral Fury
improvement_lmr
diff10.0+0.10
ELO    -2.38 +- 2.85 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 14596 W: 3588 L: 3688 D: 7320
PENTA  [37, 1773, 3768, 1693, 27]
PlentyChess Yoshie2000
no-duplicate-noisy-killer
diff8.0+0.08
ELO    -1.18 +- 1.94 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 30534 W: 7352 L: 7456 D: 15726
PENTA  [42, 3680, 7918, 3594, 33]
PlentyChess Yoshie2000
capture-killer-bonus
diff8.0+0.08
ELO    -1.26 +- 1.99 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29134 W: 7058 L: 7164 D: 14912
PENTA  [52, 3490, 7579, 3404, 42]
Quanticade DarkNeutrino
small-probcut
Small probcut
diff10.0+0.10
ELO    -1.64 +- 2.44 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 19124 W: 4453 L: 4543 D: 10128
PENTA  [31, 2276, 5034, 2194, 27]
Caissa Witek
tm-clock-disadvantage
diff8.0+0.08
ELO    3.97 +- 2.36 (95%)
LLR    2.97 (-2.94, 2.94) [0.00, 2.50]
GAMES  N: 22410 W: 5559 L: 5303 D: 11548
PENTA  [79, 2558, 5693, 2778, 97]
Integral Fury
mp_pawn_king_wall
diff10.0+0.10
ELO    -5.10 +- 3.87 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 7764 W: 1872 L: 1986 D: 3906
PENTA  [16, 965, 2036, 847, 18]
Caissa Witek
master
New neural net (eval-ml-11a-100B-spsa-transplant) ELO 3.47 +- 2.00 (95%) SPRT 10.0+0.10s Threads=1 Hash=16MB LLR 2.95 (-2.94, 2.94) [0.00, 2.00] GAMES N: 31480 W: 7633 L: 7319 D: 16528 PENTA [124, 3617, 7934, 3951, 114] https://furybench.com/test/7644/ ELO 0.98 +- 1.25 (95%) SPRT 60.0+0.60s Threads=1 Hash=128MB LLR 1.78 (-2.94, 2.94) [-0.50, 2.50] GAMES N: 70284 W: 16366 L: 16167 D: 37751 PENTA [51, 8055, 18722, 8272, 42] https://furybench.com/test/7645/
diff10.0+0.10
ELO    6.79 +- 3.81 (95%)
GAMES  N: 8594/40000 W: 2113 L: 1945 D: 4536
PENTA  [16, 990, 2138, 1116, 37]
Caissa Witek
eval-ml-11a-100B-spsa-transplant
diff60.0+0.60
ELO    1.02 +- 1.24 (95%)
LLR    1.96 (-2.94, 2.94) [-0.50, 2.50]
GAMES  N: 71636 W: 16692 L: 16481 D: 38463
PENTA  [51, 8201, 19096, 8426, 44]
Quanticade DarkNeutrino
see-depthless
search.c: Remove depth guard for SEE PVS pruning
diff10.0+0.10
ELO    -21.62 +- 9.42 (95%)
LLR    -1.49 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 1368 W: 280 L: 365 D: 723
PENTA  [10, 194, 351, 129, 0]
Quanticade DarkNeutrino
scale-adjust
nnue.c: Adjust eval scale so it matches net60 on average
diff10.0+0.10
ELO    -1.74 +- 2.95 (95%)
LLR    -1.62 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 12962 W: 2981 L: 3046 D: 6935
PENTA  [14, 1542, 3443, 1459, 23]