FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Active : 9 Machines / 158 Threads / 107.99 MNPS
Priority 0
Integral Fury
Update README
diff40.0+0.40
ELO    -0.78 +- 8.78 (95%)
GAMES  N: 1330/10000 W: 334 L: 337 D: 659
PENTA  [2, 141, 381, 140, 1]
Quanticade DarkNeutrino
25K node datagen.
diffN=25000
ELO    -0.12 +- 0.12 (95%)
GAMES  N: 21665428/30000000 W: 7601397 L: 7609134 D: 6454897
Caissa Witek
Endgames: Remove KBNvK endgame evaluator KBNvK was preferred more than other, more winning endgame, leading to draws in winning positions. STC, KBNvK_dtz60.epd: Results of New vs Old (6+0.06, 1t, 8MB, KBNvK_dtz60.epd): Elo: 95.95 +/- 12.31, nElo: 234.36 +/- 28.57 LOS: 100.00 %, DrawRatio: 45.42 %, PairsRatio: 37.75 Games: 568, Wins: 164, Losses: 11, Draws: 393, Points: 360.5 (63.47 %) Ptnml(0-2): [0, 4, 129, 145, 6], WL/DD Ratio: 0.06 LLR: 2.95 (100.0%) (-2.94, 2.94) [0.00, 5.00] STC, endgames_cdb95105.epd: ELO 11.02 +- 3.49 (95%) SPRT 10.0+0.10s Threads=1 Hash=16MB LLR 3.00 (-2.94, 2.94) [0.00, 2.00] GAMES N: 7758 W: 1948 L: 1702 D: 4108 PENTA [2, 667, 2293, 917, 0] https://furybench.com/test/7502/
diff10.0+0.10
ELO    0.32 +- 1.12 (95%)
LLR    -0.40 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 77164 W: 18417 L: 18347 D: 40400
PENTA  [15, 7947, 22585, 8023, 12]
Priority -1
Caissa Witek
Neural net: Use rounding to nearest in pairwise multiplication
diff10.0+0.10
ELO    0.47 +- 0.69 (95%)
LLR    -0.38 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 259070 W: 61746 L: 61393 D: 135931
PENTA  [963, 30900, 65436, 31293, 943]
Caissa Witek
QSearch: Fix uninitialized cont history pointers
diff10.0+0.10
ELO    -0.30 +- 1.82 (95%)
LLR    -0.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 36178 W: 8486 L: 8517 D: 19175
PENTA  [96, 4322, 9283, 4293, 95]
Finished
Integral Fury
Update README
diff40.0+0.40
ELO    5.23 +- 3.32 (95%)
LLR    2.93 (-2.25, 2.89) [0.00, 4.00]
GAMES  N: 10290 W: 2616 L: 2461 D: 5213
PENTA  [15, 1116, 2733, 1261, 20]
Integral Fury
Update README
diff10.0+0.10
ELO    6.13 +- 3.70 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 4.00]
GAMES  N: 8610 W: 2181 L: 2029 D: 4400
PENTA  [16, 954, 2216, 1100, 19]
Integral Fury
Update README
diffN=20000
ELO    4.27 +- 2.87 (95%)
LLR    2.92 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 22152 W: 6508 L: 6236 D: 9408
PENTA  [373, 2636, 4869, 2742, 456]
Integral Furydiff40.0+0.40
ELO    0.88 +- 1.10 (95%)
LLR    0.76 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 86660 W: 21353 L: 21133 D: 44174
PENTA  [30, 9575, 23896, 9803, 26]
Integral Fury
Round the pairwise FT product instead of flooring it
diff10.0+0.10
ELO    0.60 +- 1.03 (95%)
LLR    -0.83 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 109698 W: 27464 L: 27275 D: 54959
PENTA  [223, 12801, 28616, 12982, 227]
Caissa Witekdiff10.0+0.10
ELO    -0.63 +- 1.25 (95%)
LLR    -2.96 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 81132 W: 19440 L: 19586 D: 42106
PENTA  [330, 9780, 20485, 9648, 323]
Caissa Witekdiff10.0+0.10
ELO    -0.65 +- 1.27 (95%)
LLR    -2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 79348 W: 18900 L: 19049 D: 41399
PENTA  [359, 9594, 19889, 9501, 331]
Integral Furydiff40.0+0.40
ELO    2.17 +- 1.64 (95%)
LLR    2.99 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 39946 W: 9956 L: 9706 D: 20284
PENTA  [24, 4418, 10838, 4670, 23]
Integral Furydiff10.0+0.10
ELO    4.23 +- 2.65 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 17076 W: 4258 L: 4050 D: 8768
PENTA  [37, 1948, 4366, 2144, 43]
Caissa Witekdiff10.0+0.10
ELO    11.02 +- 3.49 (95%)
LLR    3.00 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 7758 W: 1948 L: 1702 D: 4108
PENTA  [2, 667, 2293, 917, 0]
Integral FurydiffN=25000
ELO    3.28 +- 2.40 (95%)
LLR    2.89 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 30086 W: 8695 L: 8411 D: 12980
PENTA  [484, 3503, 6818, 3721, 517]
Caissa Witekdiff10.0+0.10
ELO    -0.09 +- 0.89 (95%)
LLR    -3.10 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 158698 W: 37704 L: 37746 D: 83248
PENTA  [553, 19088, 40140, 18984, 584]
Illumina Mergener
Remove board listeners
diff8.0+0.08
ELO    1.59 +- 1.89 (95%)
LLR    0.71 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 37650 W: 8386 L: 8214 D: 21050
PENTA  [211, 4485, 9281, 4617, 231]
Vine SwedishChef
Merge branch 'main' into rep_fix
diff40.0+0.40
ELO    6.36 +- 5.03 (95%)
LLR    2.91 (-2.25, 2.89) [-5.00, 0.00]
GAMES  N: 4646 W: 894 L: 809 D: 2943
PENTA  [14, 485, 1246, 558, 20]
Vine SwedishChef
proper inference
diff4.0+0.04
ELO    14.01 +- 6.63 (95%)
LLR    3.15 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 3498 W: 840 L: 699 D: 1959
PENTA  [35, 363, 820, 488, 43]