FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Vine Fury
material_scaling1
diff10.0+0.10
ELO    -29.88 +- 13.49 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 1224 W: 315 L: 420 D: 489
PENTA  [53, 165, 252, 118, 24]
Vine Fury
material_scaling
diff10.0+0.10
ELO    -3.39 +- 5.48 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 7372 W: 2114 L: 2186 D: 3072
PENTA  [240, 872, 1497, 874, 203]
Vine Fury
policy_l2_concat
diff10.0+0.10
ELO    -88.34 +- 22.49 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 462 W: 85 L: 200 D: 177
PENTA  [31, 90, 74, 35, 1]
Vine Fury
policy_l2_concat
diffN=2000
ELO    -18.01 +- 11.85 (95%)
LLR    -2.38 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 2452 W: 945 L: 1072 D: 435
PENTA  [207, 190, 511, 159, 159]
Vine Fury
combined_v28_p8
diff10.0+0.10
ELO    8.61 +- 5.69 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 7302 W: 2360 L: 2179 D: 2763
PENTA  [215, 827, 1472, 836, 301]
Vine Fury
combined_v28_p8_test
diff10.0+0.10
ELO    -276.84 +- 42.42 (95%)
LLR    -2.53 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 302 W: 20 L: 220 D: 62
PENTA  [77, 48, 24, 2, 0]
Vine Fury
div_cpuct
diff40.0+0.40
ELO    -12.83 +- 12.72 (95%)
LLR    -1.11 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 1192 W: 298 L: 342 D: 552
PENTA  [37, 140, 267, 134, 18]
Vine Fury
div_cpuct
diff10.0+0.10
ELO    1.02 +- 11.67 (95%)
LLR    -0.07 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 1706 W: 512 L: 507 D: 687
PENTA  [59, 192, 341, 207, 54]
Vine Fury
variance_q_cpuct
diff10.0+0.10
ELO    -28.71 +- 13.20 (95%)
LLR    -2.32 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 1298 W: 339 L: 446 D: 513
PENTA  [54, 177, 272, 114, 32]
Vine Fury
policy_entropy_cpuct
diff10.0+0.10
ELO    -68.92 +- 20.43 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 618 W: 142 L: 263 D: 213
PENTA  [41, 103, 113, 40, 12]
Vine Fury
[Anura] main
diff10.0+0.10
ELO    -34.33 +- 11.73 (95%)
GAMES  N: 2000/2000 W: 547 L: 744 D: 709
PENTA  [109, 298, 343, 181, 69]
Vine Fury
combined_v26_p7_test
diff10.0+0.10
ELO    7.80 +- 5.27 (95%)
LLR    2.97 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 8512 W: 2759 L: 2568 D: 3185
PENTA  [286, 910, 1689, 1069, 302]
Vine Fury
cpuct_visit_tweak
diff40.0+0.40
ELO    -5.96 +- 6.40 (95%)
LLR    -2.36 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 4956 W: 1328 L: 1413 D: 2215
PENTA  [126, 628, 1048, 557, 119]
Vine Fury
cpuct_visit_tweak
diff10.0+0.10
ELO    -8.29 +- 13.17 (95%)
LLR    -0.79 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 1342 W: 402 L: 434 D: 506
PENTA  [44, 175, 265, 143, 44]
Vine Fury
cpuct_visit_scaling
diff40.0+0.40
ELO    56.27 +- 15.92 (95%)
LLR    2.94 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 928 W: 322 L: 173 D: 433
PENTA  [8, 89, 168, 144, 55]
Vine Fury
combined_v25_p6
diff10.0+0.10
ELO    5.72 +- 4.23 (95%)
LLR    2.92 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 11846 W: 3181 L: 2986 D: 5679
PENTA  [308, 1373, 2373, 1554, 315]
Vine Fury
cpuct_visit_scaling
diff10.0+0.10
ELO    9.45 +- 5.92 (95%)
LLR    2.95 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 6396 W: 1889 L: 1715 D: 2792
PENTA  [149, 770, 1276, 764, 239]
Vine Fury
combined_v25_p6_test1
diff10.0+0.10
ELO    -6.93 +- 7.08 (95%)
LLR    -2.34 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 4566 W: 1227 L: 1318 D: 2021
PENTA  [148, 591, 885, 522, 137]
Vine Fury
combined_v25_p5
diff10.0+0.10
ELO    25.08 +- 10.07 (95%)
LLR    3.05 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 2220 W: 685 L: 525 D: 1010
PENTA  [51, 230, 415, 336, 78]
Vine Fury
policy_512hl
diff10.0+0.10
ELO    53.52 +- 14.93 (95%)
LLR    2.97 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 988 W: 346 L: 195 D: 447
PENTA  [14, 76, 198, 157, 49]
Vine Fury
combined_v25_p4_test
diff10.0+0.10
ELO    -7.07 +- 7.02 (95%)
LLR    -2.43 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 4666 W: 1227 L: 1322 D: 2117
PENTA  [161, 594, 883, 569, 126]
Vine Fury
combined_v25_p3
diff10.0+0.10
ELO    21.68 +- 9.50 (95%)
LLR    3.01 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 2632 W: 862 L: 698 D: 1072
PENTA  [73, 269, 500, 369, 105]
Vine Fury
datagen_temperature
diffN=1000
ELO    -0.26 +- 0.76 (95%)
GAMES  N: 661340/650000 W: 270578 L: 271064 D: 119698
Vine Fury
throw_imbalanced_openings
diffN=1000
ELO    0.16 +- 0.30 (95%)
GAMES  N: 4000074/4000000 W: 1557774 L: 1555907 D: 886393
Vine Fury
main
diffN=1000
ELO    -0.12 +- 0.30 (95%)
GAMES  N: 4012912/4000000 W: 1606216 L: 1607600 D: 799096