FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Integral Fury
qs_fp_tweak
diff10.0+0.10
ELO    1.20 +- 0.98 (95%)
LLR    2.89 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 129344 W: 31218 L: 30770 D: 67356
PENTA  [424, 15327, 32733, 15753, 435]
Integral Fury
low_depth_se
diff10.0+0.10
ELO    -0.93 +- 1.84 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 35926 W: 8522 L: 8618 D: 18786
PENTA  [109, 4324, 9195, 4224, 111]
Integral Fury
spsa_12225
diff60.0+0.60
ELO    6.98 +- 3.21 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 10700 W: 2590 L: 2375 D: 5735
PENTA  [4, 1145, 2840, 1354, 7]
Integral Fury
spsa_12225
diff10.0+0.10
ELO    2.33 +- 2.24 (95%)
LLR    1.66 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 24584 W: 6023 L: 5858 D: 12703
PENTA  [77, 2877, 6228, 3024, 86]
Integral Fury
spsa
diff60.0+0.60
TUNE   95 parameters
ITER   12,255 / 12,500
GAMES  98,044 / 100,000
Integral Fury
spsa_6600
diff60.0+0.60
ELO    4.99 +- 6.07 (95%)
LLR    0.81 (-2.25, 2.89) [0.00, 4.00]
GAMES  N: 2924 W: 710 L: 668 D: 1546
PENTA  [3, 308, 796, 354, 1]
Integral Fury
spsa_2500
diff60.0+0.60
ELO    8.07 +- 5.82 (95%)
LLR    1.02 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 3186 W: 777 L: 703 D: 1706
PENTA  [2, 328, 857, 406, 0]
Integral Fury
see_catchup
diff10.0+0.10
ELO    0.66 +- 1.28 (95%)
LLR    0.04 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 75416 W: 18434 L: 18291 D: 38691
PENTA  [286, 8810, 19361, 8977, 274]
Integral Fury
spsa
diff10.0+0.10
ELO    -28.00 +- 10.67 (95%)
LLR    -2.27 (-2.25, 2.89) [-5.00, 0.00]
GAMES  N: 1082 W: 193 L: 280 D: 609
PENTA  [6, 170, 273, 89, 3]
Integral Fury
bad_quiets1
diff10.0+0.10
ELO    -2.19 +- 2.48 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 19868 W: 4768 L: 4893 D: 10207
PENTA  [74, 2396, 5110, 2289, 65]
Integral Fury
wdl-filtered-redo
diff10.0+0.10
ELO    -17.96 +- 9.25 (95%)
LLR    -1.04 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 1394 W: 301 L: 373 D: 720
PENTA  [6, 193, 371, 121, 6]
Integral Fury
bad_quiets
diff10.0+0.10
ELO    -1.69 +- 3.97 (95%)
LLR    -0.73 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 7822 W: 1859 L: 1897 D: 4066
PENTA  [28, 949, 1990, 921, 23]
Integral Fury
bad_quiets
diff10.0+0.10
ELO    -88.74 +- 13.79 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 896 W: 181 L: 405 D: 310
PENTA  [44, 175, 192, 35, 2]
Integral Fury
lmp_eval_imp
diff40.0+0.40
ELO    2.07 +- 2.25 (95%)
LLR    1.37 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 22460 W: 5319 L: 5185 D: 11956
PENTA  [21, 2595, 5864, 2729, 21]
Integral Fury
dual_activation
diff10.0+0.10
ELO    -2.24 +- 2.82 (95%)
LLR    -1.84 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 16106 W: 3872 L: 3976 D: 8258
PENTA  [84, 1957, 4054, 1895, 63]
Integral Fury
dual_activation
diffN=25000
ELO    -1.61 +- 2.60 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29566 W: 8666 L: 8803 D: 12097
PENTA  [726, 3561, 6338, 3440, 718]
Integral Fury
lmp_eval_imp
diff10.0+0.10
ELO    3.13 +- 2.06 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29168 W: 7117 L: 6854 D: 15197
PENTA  [93, 3394, 7355, 3641, 101]
Integral Fury
quadratic_razoring
diff10.0+0.10
ELO    -0.40 +- 1.50 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 54276 W: 12949 L: 13011 D: 28316
PENTA  [166, 6527, 13807, 6479, 159]
Integral Fury
eval_policy_tweak
diff10.0+0.10
ELO    -2.56 +- 3.59 (95%)
LLR    -1.24 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 9618 W: 2276 L: 2347 D: 4995
PENTA  [48, 1151, 2461, 1122, 27]
Integral Fury
quadratic_razoring
diff10.0+0.10
ELO    0.30 +- 4.18 (95%)
LLR    -0.09 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 6932 W: 1647 L: 1641 D: 3644
PENTA  [26, 806, 1787, 830, 17]
Integral Fury
ttpv_cutnode_lmr
diff10.0+0.10
ELO    0.03 +- 1.16 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 91618 W: 21993 L: 21986 D: 47639
PENTA  [301, 11051, 23110, 11034, 313]
Integral Fury
wdl_filtered
diffN=25000
ELO    -81.54 +- 14.91 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 1024 W: 192 L: 428 D: 404
PENTA  [67, 183, 189, 65, 8]
Integral Fury
eval_policy_tweak
diff10.0+0.10
ELO    -0.86 +- 2.45 (95%)
LLR    -1.23 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 20230 W: 4816 L: 4866 D: 10548
PENTA  [61, 2428, 5178, 2396, 52]
Integral Fury
ttpv_cutnode_lmr
diff10.0+0.10
ELO    0.52 +- 2.55 (95%)
LLR    -0.09 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 18826 W: 4559 L: 4531 D: 9736
PENTA  [58, 2228, 4815, 2252, 60]
Integral Fury
zekrom-redo-v2
diff40.0+0.40
ELO    -8.58 +- 4.44 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 5956 W: 1355 L: 1502 D: 3099
PENTA  [16, 773, 1539, 642, 8]