FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Integral Fury
optimism_again1
diff10.0+0.10
ELO    -1.65 +- 2.20 (95%)
LLR    -2.36 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 25616 W: 6267 L: 6389 D: 12960
PENTA  [97, 3116, 6484, 3034, 77]
Integral Fury
optimism_again
diff10.0+0.10
ELO    -5.54 +- 3.63 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 8970 W: 2154 L: 2297 D: 4519
PENTA  [29, 1114, 2329, 997, 16]
Integral Fury
move_mat_scaling_to_search
diff10.0+0.10
ELO    2.85 +- 3.00 (95%)
LLR    2.91 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 13284 W: 3310 L: 3201 D: 6773
PENTA  [41, 1509, 3419, 1646, 27]
Integral Fury
larger_correction_bonus
diff10.0+0.10
ELO    -18.06 +- 6.26 (95%)
LLR    -2.40 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 3254 W: 720 L: 889 D: 1645
PENTA  [20, 470, 802, 329, 6]
Integral Fury
tt_move_qs_extend
diff10.0+0.10
ELO    -4.20 +- 3.23 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 11572 W: 2765 L: 2905 D: 5902
PENTA  [23, 1482, 2919, 1336, 26]
Integral Fury
update_corr_badcap
diff10.0+0.10
ELO    -4.29 +- 3.26 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 11252 W: 2691 L: 2830 D: 5731
PENTA  [26, 1422, 2867, 1287, 24]
Integral Fury
optimism_scaling
diff10.0+0.10
ELO    -4.29 +- 3.25 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 11348 W: 2771 L: 2911 D: 5666
PENTA  [43, 1387, 2934, 1287, 23]
Integral Fury
conthist_capture_incheck
diff40.0+0.40
ELO    -1.19 +- 1.93 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29518 W: 7171 L: 7272 D: 15075
PENTA  [26, 3453, 7892, 3372, 16]
Integral Fury
qs_use_tt_eval_in_check
diff10.0+0.10
ELO    -0.42 +- 1.49 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 52670 W: 12898 L: 12961 D: 26811
PENTA  [159, 6087, 13888, 6060, 141]
Integral Fury
conthist_capture_incheck
diff40.0+0.40
ELO    -44.79 +- 9.68 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 1248 W: 210 L: 370 D: 668
PENTA  [6, 233, 300, 85, 0]
Integral Fury
conthist_capture_incheck
diff40.0+0.40
ELO    -0.48 +- 3.57 (95%)
LLR    -0.40 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 8658 W: 2065 L: 2077 D: 4516
PENTA  [9, 998, 2330, 980, 12]
Vine Fury
relax_backprop
diff10.0+0.10
ELO    -9.06 +- 6.89 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 2878 W: 551 L: 626 D: 1701
PENTA  [39, 332, 745, 311, 12]
Vine Fury
relax_backprop
diff10.0+0.10
ELO    -122.66 +- 31.08 (95%)
LLR    -1.05 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 174 W: 7 L: 66 D: 101
PENTA  [9, 45, 29, 4, 0]
Vine Fury
relax_backprop
diff10.0+0.10
ELO    -360.20 +- 97.99 (95%)
LLR    -0.85 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 94 W: 0 L: 73 D: 21
PENTA  [29, 15, 3, 0, 0]
Vine Fury
combined_v58_p22_test
diff10.0+0.10
ELO    -2.48 +- 4.16 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 7690 W: 1516 L: 1571 D: 4603
PENTA  [51, 923, 1955, 862, 54]
Integral Fury
latest_vine_smallnet
diff10.0+0.10
ELO    -2.95 +- 2.85 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 15908 W: 3892 L: 4027 D: 7989
PENTA  [83, 1991, 3899, 1940, 41]
Vine Fury
less_temp_dg
diffN=100000
ELO    7.86 +- 4.84 (95%)
LLR    3.13 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 7164 W: 1770 L: 1608 D: 3786
PENTA  [108, 767, 1686, 897, 124]
Integral Fury
latest_vine_smallnet
diff40.0+0.40
ELO    -25.87 +- 6.29 (95%)
GAMES  N: 3000/3000 W: 618 L: 841 D: 1541
PENTA  [1, 492, 747, 249, 11]
Vine Fury
datagen_conditions
diffN=100000
ELO    11.16 +- 7.78 (95%)
GAMES  N: 3114/3000 W: 852 L: 752 D: 1510
PENTA  [61, 338, 659, 438, 61]
Vine Fury
datagen_conditions
diffN=100000
ELO    6.93 +- 12.45 (95%)
GAMES  N: 1304/40000 W: 359 L: 333 D: 612
PENTA  [30, 148, 272, 170, 32]
Integral Fury
[Vine] datagen_conditions
time odds diffN=20000
ELO    321.57 +- 20.05 (95%)
GAMES  N: 1024/3000 W: 761 L: 15 D: 248
PENTA  [0, 2, 22, 228, 260]
Integral Fury
latest_vine_smallnet
diff10.0+0.10
ELO    -13.38 +- 5.90 (95%)
LLR    -2.09 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 3974 W: 947 L: 1100 D: 1927
PENTA  [14, 597, 937, 406, 33]
Integral Fury
latest_vine_smallnet
diff40.0+0.40
ELO    4.36 +- 2.49 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 18886 W: 4691 L: 4454 D: 9741
PENTA  [35, 2149, 4819, 2424, 16]
Vine Fury
var_scaling_again
diff10.0+0.10
ELO    0.00 +- 0.00 (95%)
LLR    0.00 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 0 W: 0 L: 0 D: 0
PENTA  [0, 0, 0, 0, 0]
Vine Fury
spsa
diff40.0+0.40
TUNE   14 parameters
ITER   6,251 / 6,250
GAMES  50,008 / 50,000