FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Active : 24 Machines / 304 Threads / 247.62 MNPS
Priority 0
Caissa Witek
razoring-no-depth-limit
diff8.0+0.08
ELO    2.45 +- 4.83 (95%)
LLR    0.67 (-2.94, 2.94) [-2.50, 0.00]
GAMES  N: 5386 W: 1325 L: 1287 D: 2774
PENTA  [23, 610, 1397, 632, 31]
PlentyChess Yoshie2000
real-contcorr-3
crash diff40.0+0.40
ELO    0.81 +- 1.65 (95%)
LLR    0.36 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 38218 W: 9284 L: 9195 D: 19739
PENTA  [4, 4236, 10541, 4323, 5]
PlentyChess Yoshie2000
capture-killer-bonus
diff8.0+0.08
ELO    1.30 +- 3.38 (95%)
LLR    0.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 10146 W: 2502 L: 2464 D: 5180
PENTA  [21, 1169, 2650, 1217, 16]
Caissa Witek
see-prune-capture-history
diff10.0+0.10
ELO    1.15 +- 2.96 (95%)
LLR    0.28 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 13956 W: 3334 L: 3288 D: 7334
PENTA  [54, 1621, 3567, 1697, 39]
Quanticade DarkNeutrino
small-probcut
Small probcut
diff10.0+0.10
ELO    1.16 +- 4.04 (95%)
LLR    0.14 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 7196 W: 1725 L: 1701 D: 3770
PENTA  [12, 848, 1857, 866, 15]
Caissa Witek
tm-clock-disadvantage
diff8.0+0.08
ELO    4.70 +- 18.08 (95%)
LLR    0.06 (-2.94, 2.94) [0.00, 2.50]
GAMES  N: 370 W: 88 L: 83 D: 199
PENTA  [1, 42, 93, 49, 0]
PlentyChess Yoshie2000
no-duplicate-noisy-killer
diff8.0+0.08
ELO    0.73 +- 3.69 (95%)
LLR    0.03 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 8606 W: 2112 L: 2094 D: 4400
PENTA  [15, 1024, 2202, 1052, 10]
Quanticade DarkNeutrino
ldse-correction
search.c: Apply correction to ldse extensions
diff60.0+0.60
ELO    -4.61 +- 10.80 (95%)
LLR    -0.23 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 754 W: 159 L: 169 D: 426
PENTA  [0, 76, 235, 66, 0]
Integral Fury
mp_pawn_king_wall
diff10.0+0.10
ELO    -8.89 +- 6.95 (95%)
LLR    -1.16 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 2462 W: 579 L: 642 D: 1241
PENTA  [4, 329, 630, 262, 6]
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]
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
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]
Quanticade DarkNeutrino
[Integral] main
Lets see how bad it is
diff10.0+0.10
ELO    -48.77 +- 6.94 (95%)
GAMES  N: 2488/10000 W: 428 L: 775 D: 1285
PENTA  [13, 487, 581, 160, 3]
Quanticade DarkNeutrino
master
net61 (#439)
diff60.0+0.60
ELO    95.59 +- 13.95 (95%)
GAMES  N: 544/40000 W: 211 L: 65 D: 268
PENTA  [0, 16, 96, 158, 2]
Quanticade DarkNeutrino
master
net61 (#439)
diff10.0+0.10
ELO    113.60 +- 4.71 (95%)
GAMES  N: 6292/10000 W: 2716 L: 729 D: 2847
PENTA  [8, 158, 1030, 1739, 211]
Quanticade DarkNeutrino
net61
net61
diff60.0+0.60
ELO    10.33 +- 4.27 (95%)
LLR    2.89 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 5788 W: 1464 L: 1292 D: 3032
PENTA  [1, 570, 1582, 738, 3]
PlentyChess Yoshie2000
real-contcorr-3
diff8.0+0.08
ELO    0.43 +- 1.44 (95%)
LLR    -0.45 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 55524 W: 13552 L: 13484 D: 28488
PENTA  [59, 6555, 14492, 6571, 85]
Quanticade DarkNeutrino
net61
TIPP chonker relabel + 3B of 25k node data
diff10.0+0.10
ELO    10.81 +- 4.53 (95%)
LLR    2.89 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 5982 W: 1525 L: 1339 D: 3118
PENTA  [15, 636, 1508, 812, 20]
Caissa Witek
eval-tempo-curve
Eval tempo curve
diff10.0+0.10
ELO    0.48 +- 0.73 (95%)
LLR    -0.27 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 230884 W: 54570 L: 54250 D: 122064
PENTA  [858, 27472, 58400, 27916, 796]
PlentyChess Yoshie2000
fix-repetition-warnings
diffN=20000
ELO    0.15 +- 0.15 (95%)
LLR    3.07 (-2.25, 2.89) [-5.00, 0.00]
GAMES  N: 9356 W: 2532 L: 2528 D: 4296
PENTA  [0, 0, 4674, 4, 0]
PlentyChess Yoshie2000
fix-repetition-warnings
diff8.0+0.08
ELO    -4.45 +- 3.60 (95%)
LLR    -2.29 (-2.25, 2.89) [-5.00, 0.00]
GAMES  N: 8050 W: 1910 L: 2013 D: 4127
PENTA  [17, 894, 2302, 799, 13]
PlentyChess Yoshie2000
real-contcorr-2
diff8.0+0.08
ELO    -0.50 +- 1.54 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 48846 W: 11768 L: 11838 D: 25240
PENTA  [68, 5830, 12694, 5766, 65]
PlentyChess Yoshie2000
real-contcorr
diff8.0+0.08
ELO    -1.80 +- 2.24 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 22588 W: 5458 L: 5575 D: 11555
PENTA  [32, 2687, 5972, 2572, 31]