FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Quanticade DarkNeutrino
more-se-depth
crash diff8.0+0.08
ELO    0.78 +- 0.96 (95%)
LLR    -0.12 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 143210 W: 32893 L: 32572 D: 77745
PENTA  [767, 16962, 35804, 17327, 745]
Integral Fury
narrow_alpha_fail_high
diff10.0+0.10
ELO    -0.50 +- 1.78 (95%)
LLR    -1.77 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 38510 W: 9217 L: 9272 D: 20021
PENTA  [124, 4626, 9799, 4593, 113]
PlentyChess Yoshie2000
eval-policy-tune
diff80.0+0.80
ELO    7.98 +- 4.55 (95%)
LLR    1.60 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 4878 W: 1270 L: 1158 D: 2450
PENTA  [1, 474, 1376, 588, 0]
PlentyChess Yoshie2000
eval-policy-tune
diff8.0+0.08
ELO    4.28 +- 2.46 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 19234 W: 4755 L: 4518 D: 9961
PENTA  [39, 2150, 4999, 2393, 36]
Integral Fury
narrow_alpha_fail_high
diff10.0+0.10
ELO    -3.42 +- 5.83 (95%)
LLR    -0.60 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 3754 W: 897 L: 934 D: 1923
PENTA  [21, 458, 949, 435, 14]
PlentyChess Yoshie2000
eval-policy-tune
crash diff80.0+0.80
TUNE   76 parameters
ITER   10,000 / 10,000
GAMES  160,002 / 160,000
Illumina Mergener
nmp-tt
diff8.0+0.08
ELO    1.37 +- 1.09 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 113640 W: 24813 L: 24366 D: 64461
PENTA  [705, 13524, 27990, 13821, 780]
Obsidian SwedishChef
see_pinned
diff10.0+0.10
ELO    -3.60 +- 3.54 (95%)
LLR    -1.27 (-2.25, 2.89) [0.00, 2.00]
GAMES  N: 9468 W: 2280 L: 2378 D: 4810
PENTA  [22, 1171, 2450, 1065, 26]
Obsidian Gabe
last-thing-before-tune
diff10.0+0.10
ELO    -2.02 +- 2.56 (95%)
LLR    -0.89 (-2.25, 2.89) [-2.00, 0.00]
GAMES  N: 17738 W: 4269 L: 4372 D: 9097
PENTA  [43, 2104, 4678, 2001, 43]
Quanticade DarkNeutrino
ttpv-lmr
diff8.0+0.08
ELO    -13.18 +- 6.15 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 3534 W: 744 L: 878 D: 1912
PENTA  [29, 477, 875, 371, 15]
Caissa Witek
counter_move_update
diff10.0+0.10
ELO    -0.41 +- 1.11 (95%)
LLR    -2.96 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 99998 W: 23438 L: 23555 D: 53005
PENTA  [328, 12087, 25291, 11960, 333]
Quanticade DarkNeutrino
iir-cutnode
crash diff8.0+0.08
ELO    -1.05 +- 2.24 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 26106 W: 5977 L: 6056 D: 14073
PENTA  [115, 3231, 6468, 3096, 143]
Quanticade DarkNeutrino
lmr-root
diff8.0+0.08
ELO    -2.63 +- 3.04 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 14256 W: 3199 L: 3307 D: 7750
PENTA  [88, 1743, 3564, 1655, 78]
Quanticade DarkNeutrino
lmr-improving-2
diff8.0+0.08
ELO    -6.21 +- 4.32 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6882 W: 1504 L: 1627 D: 3751
PENTA  [45, 850, 1760, 755, 31]
Quanticade DarkNeutrino
lmr-fix-reductions
diff8.0+0.08
ELO    -6.48 +- 4.64 (95%)
LLR    -2.26 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 6116 W: 1318 L: 1432 D: 3366
PENTA  [36, 787, 1521, 683, 31]