FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Caissa Witek
tweak_hist_prun
diff10.0+0.10
ELO    -4.33 +- 2.57 (95%)
LLR    -2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 19186 W: 4435 L: 4674 D: 10077
PENTA  [89, 2393, 4852, 2186, 73]
Quanticade DarkNeutrino
net45
diff10.0+0.10
ELO    -0.17 +- 4.68 (95%)
LLR    -0.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 5972 W: 1462 L: 1465 D: 3045
PENTA  [28, 729, 1476, 724, 29]
Quanticade DarkNeutrino
qs-see-more-margin
crash diff10.0+0.10
ELO    -1.20 +- 2.23 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 23438 W: 5312 L: 5393 D: 12733
PENTA  [56, 2766, 6159, 2679, 59]
Caissa Witek
lmrscale_1024
diff10.0+0.10
ELO    2.45 +- 2.50 (95%)
LLR    2.98 (-2.94, 2.94) [-2.75, 0.25]
GAMES  N: 20122 W: 4861 L: 4719 D: 10542
PENTA  [69, 2373, 5048, 2489, 82]
PlentyChess Yoshie2000
[Stockfish] 951503A399C693A8
time odds diffN=7500
ELO    2.66 +- 0.19 (95%)
GAMES  N: 9323364/10000000 W: 3518400 L: 3446973 D: 2357991
PlentyChess Yoshie2000
datagen-into-main
diff8.0+0.08
ELO    11.72 +- 21.20 (95%)
GAMES  N: 178/100 W: 43 L: 37 D: 98
PENTA  [0, 12, 59, 18, 0]
Caissa Witek
datagen
diffN=40000
ELO    40.68 +- 5.93 (95%)
GAMES  N: 5002/20000 W: 1746 L: 1163 D: 2093
PENTA  [44, 424, 1078, 815, 140]
Caissa Witek
datagen_tuned_4
diffN=40000
ELO    3.56 +- 2.17 (95%)
LLR    2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 37228 W: 10564 L: 10183 D: 16481
PENTA  [599, 4395, 8302, 4662, 656]
Quanticade DarkNeutrino
master
diffN=25000
ELO    -0.14 +- 0.28 (95%)
GAMES  N: 3949954/10000000 W: 1324710 L: 1326316 D: 1298928
Caissa Witek
datagen_tuning
diffN=40000
TUNE   40 parameters
ITER   23,367 / 25,000
GAMES  747,764 / 800,000
Pawnocchio SwedishChef
more_precision
diff10.0+0.10
ELO    1.17 +- 0.90 (95%)
LLR    2.91 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 145072 W: 34401 L: 33914 D: 76757
PENTA  [284, 17117, 37287, 17524, 324]
Caissa Witek
eval-74-202B
diff10.0+0.10
ELO    -0.27 +- 1.37 (95%)
LLR    -1.66 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 66124 W: 15573 L: 15624 D: 34927
PENTA  [242, 7891, 16812, 7910, 207]
Caissa Witek
eval-73-254B
diff40.0+0.40
ELO    0.57 +- 1.05 (95%)
LLR    -0.19 (-2.94, 2.94) [0.00, 2.50]
GAMES  N: 100992 W: 22975 L: 22809 D: 55208
PENTA  [98, 11771, 26581, 11959, 87]
Quanticade DarkNeutrino
master
diff60.0+0.60
ELO    12.81 +- 6.78 (95%)
GAMES  N: 2632/5000 W: 714 L: 617 D: 1301
PENTA  [5, 273, 666, 364, 8]
PlentyChess Yoshie2000
pcm-very-bad-depth
diff8.0+0.08
ELO    0.02 +- 1.13 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 89878 W: 21906 L: 21902 D: 46070
PENTA  [157, 10555, 23517, 10547, 163]