FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
PlentyChess Yoshie2000
extend-newdepth
diff40.0+0.40
ELO    -1.60 +- 3.08 (95%)
LLR    -1.05 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 10842 W: 2699 L: 2749 D: 5394
PENTA  [5, 1205, 3049, 1159, 3]
PlentyChess Yoshie2000
extend-newdepth
diff8.0+0.08
ELO    2.65 +- 1.80 (95%)
LLR    3.05 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 37042 W: 9308 L: 9025 D: 18709
PENTA  [98, 4229, 9604, 4472, 118]
PlentyChess Yoshie2000
smp-spsa
crash smp diff40.0+0.40
TUNE   153 parameters
ITER   3,048 / 25,000
GAMES  48,772 / 400,000
PlentyChess Yoshie2000
smp-spsa
diff8.0+0.08
ELO    1.86 +- 1.64 (95%)
LLR    2.21 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 42356 W: 10460 L: 10233 D: 21663
PENTA  [61, 4829, 11160, 5078, 50]
PlentyChess Yoshie2000
smp-spsa
diff40.0+0.40
ELO    1.23 +- 2.35 (95%)
LLR    0.53 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 19188 W: 4721 L: 4653 D: 9814
PENTA  [12, 2116, 5268, 2188, 10]
Vine SwedishChef
wdl_outputs
diff10.0+0.10
ELO    -45.60 +- 14.89 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 728 W: 127 L: 222 D: 379
PENTA  [12, 139, 150, 58, 5]
Vine SwedishChef
wdl_outputs
diffN=10000
ELO    -49.73 +- 15.89 (95%)
LLR    -2.54 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 816 W: 169 L: 285 D: 362
PENTA  [35, 131, 166, 67, 9]
PlentyChess Yoshie2000
smp-spsa
smp diff40.0+0.40
ELO    5.40 +- 2.93 (95%)
LLR    2.91 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 11450 W: 2871 L: 2693 D: 5886
PENTA  [1, 1126, 3292, 1306, 0]
Pawnocchio SwedishChef
512_testnet_vine_01_12.nnue
diff40.0+0.40
ELO    2.84 +- 2.05 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 28380 W: 7264 L: 7032 D: 14084
PENTA  [54, 3316, 7211, 3562, 47]
Caissa Witek
eval-69-9B
diffN=25000
ELO    -4.06 +- 2.84 (95%)
LLR    -2.98 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 25264 W: 7529 L: 7824 D: 9911
PENTA  [686, 3022, 5448, 2853, 623]
Pawnocchio SwedishChef
512_testnet_vine_01_12.nnue
diff10.0+0.10
ELO    0.64 +- 2.83 (95%)
LLR    -0.12 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 16380 W: 4173 L: 4143 D: 8064
PENTA  [81, 1971, 4059, 1995, 84]
Pawnocchio SwedishChef
512_testnet_vine_01_11.nnue
diff10.0+0.10
ELO    2.35 +- 1.82 (95%)
LLR    2.92 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 41814 W: 11089 L: 10806 D: 19919
PENTA  [325, 4858, 10179, 5299, 246]
Integral Fury
vine_less_kld
diff40.0+0.40
ELO    -25.86 +- 6.38 (95%)
GAMES  N: 3002/3000 W: 584 L: 807 D: 1611
PENTA  [0, 500, 742, 241, 18]
Caissa Witek
eval_scale_128
diff10.0+0.10
ELO    -6.01 +- 2.97 (95%)
LLR    -2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 14170 W: 3279 L: 3524 D: 7367
PENTA  [48, 1843, 3546, 1602, 46]
Pawnocchio SwedishChef
2048pw
diff10.0+0.10
ELO    2.33 +- 1.77 (95%)
LLR    2.92 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 37942 W: 9374 L: 9120 D: 19448
PENTA  [75, 4416, 9746, 4648, 86]