FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Integral Fury
bad_noisy_fp_again
diff10.0+0.10
ELO    0.23 +- 1.20 (95%)
LLR    -1.11 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 71276 W: 17569 L: 17521 D: 36186
PENTA  [152, 7209, 20900, 7193, 184]
PlentyChess Yoshie2000
sf-integral-asp-win
diff8.0+0.08
ELO    0.68 +- 0.57 (95%)
LLR    0.87 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 360740 W: 88350 L: 87641 D: 184749
PENTA  [546, 42411, 93822, 42970, 621]
Pawnocchio SwedishChef
see_pruning_alpha
diff10.0+0.10
ELO    -0.93 +- 3.24 (95%)
LLR    -0.96 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 11612 W: 2742 L: 2773 D: 6097
PENTA  [32, 1410, 2953, 1379, 32]
Quanticade DarkNeutrino
net41
diff60.0+0.60
ELO    -23.49 +- 8.84 (95%)
LLR    -1.73 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 1422 W: 286 L: 382 D: 754
PENTA  [3, 212, 375, 120, 1]
Quanticade DarkNeutrino
net41
diffN=5000
ELO    21.56 +- 2.22 (95%)
GAMES  N: 40320/40000 W: 10623 L: 8124 D: 21573
PENTA  [713, 4159, 8362, 5768, 1158]
Pawnocchio SwedishChef
tunable_refactor
diff10.0+0.10
ELO    0.16 +- 1.28 (95%)
LLR    2.93 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 66924 W: 16017 L: 15987 D: 34920
PENTA  [155, 7256, 18617, 7272, 162]
Caissa Witek
speedup2
diff5.0+0.05
ELO    2.82 +- 2.03 (95%)
LLR    2.97 (-2.94, 2.94) [-0.50, 2.00]
GAMES  N: 31082 W: 7678 L: 7426 D: 15978
PENTA  [163, 3489, 8010, 3691, 188]
Integral Fury
bad_noisy_cn_lmr
diff10.0+0.10
ELO    -0.03 +- 1.78 (95%)
LLR    -1.03 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 38264 W: 9506 L: 9509 D: 19249
PENTA  [108, 4590, 9745, 4575, 114]
Pawnocchio SwedishChef
[Obsidian] v16.0
diff10.0+0.10
ELO    -8.14 +- 3.72 (95%)
GAMES  N: 10030/10000 W: 2501 L: 2736 D: 4793
PENTA  [51, 1395, 2377, 1122, 70]
Integral Fury
optimism_again1
diff40.0+0.40
ELO    -1.18 +- 3.24 (95%)
LLR    -0.82 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 10922 W: 2601 L: 2638 D: 5683
PENTA  [11, 1326, 2821, 1295, 8]
Integral Fury
eval_correction_lmr2
diff10.0+0.10
ELO    -2.43 +- 3.91 (95%)
LLR    -0.98 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 7880 W: 1890 L: 1945 D: 4045
PENTA  [21, 965, 2024, 908, 22]
Quanticade DarkNeutrino
net40
diff10.0+0.10
ELO    -3.17 +- 1.93 (95%)
LLR    -2.95 (-2.94, 2.94) [-2.00, 0.00]
GAMES  N: 36782 W: 9101 L: 9437 D: 18244
PENTA  [248, 4621, 8978, 4307, 237]
Integral Fury
eval_correction_lmr
diff10.0+0.10
ELO    -1.49 +- 2.50 (95%)
LLR    -1.67 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 19390 W: 4772 L: 4855 D: 9763
PENTA  [54, 2336, 5014, 2221, 70]
Caissa Witek
master
frc diff10.0+0.10
ELO    15.95 +- 2.31 (95%)
GAMES  N: 23978/40000 W: 4988 L: 3888 D: 15102
PENTA  [146, 2105, 6491, 2997, 250]
Pawnocchio SwedishChef
tripleact
diff10.0+0.10
ELO    -8.21 +- 4.79 (95%)
LLR    -2.32 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 5374 W: 1256 L: 1383 D: 2735
PENTA  [23, 693, 1376, 578, 17]