FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Integral SwedishChef
ti_tweaks
diff4.0+0.04
ELO    1.72 +- 2.04 (95%)
LLR    1.29 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 30462 W: 7831 L: 7680 D: 14951
PENTA  [181, 3356, 8008, 3503, 183]
Quanticade DarkNeutrino
opts
Optimizations
diff4.0+0.04
ELO    5.96 +- 3.19 (95%)
LLR    3.02 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 12070 W: 3064 L: 2857 D: 6149
PENTA  [51, 1275, 3194, 1446, 69]
Integral Fury
ti_tweaks
diff10.0+0.10
ELO    -2.26 +- 2.57 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 20016 W: 5020 L: 5150 D: 9846
PENTA  [123, 2448, 4964, 2382, 91]
Quanticade DarkNeutrino
net57
1024 L1
diff60.0+0.60
ELO    -2.65 +- 3.59 (95%)
LLR    -1.46 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8376 W: 1951 L: 2015 D: 4410
PENTA  [3, 994, 2260, 926, 5]
Quanticade DarkNeutrino
net57
How much is it without the slowdown
diffN=5000
ELO    13.79 +- 2.53 (95%)
GAMES  N: 40102/40000 W: 13973 L: 12382 D: 13747
PENTA  [1418, 4160, 7797, 4765, 1911]
Integral SwedishChef
ti_tweaks
diff4.0+0.04
ELO    -0.06 +- 2.29 (95%)
LLR    -0.67 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 23574 W: 6023 L: 6027 D: 11524
PENTA  [159, 2527, 6405, 2551, 145]
Integral Fury
nnue_threat_inputs
Little optimization
crash diff40.0+0.40
ELO    -8.37 +- 5.97 (95%)
LLR    -1.20 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 3198 W: 759 L: 836 D: 1603
PENTA  [9, 402, 848, 337, 3]
Quanticade DarkNeutrino
lmr-rework-tune
Will it gain ? Only one way to find out
smp diff20.0+0.20
ELO    -0.26 +- 5.05 (95%)
LLR    -0.20 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 3956 W: 942 L: 945 D: 2069
PENTA  [1, 427, 1125, 424, 1]
Quanticade DarkNeutrino
lmr-rework
lets tune the new LMR so it can beat master
smp diff20.0+0.20
TUNE   129 parameters
ITER   3,173 / 10,000
GAMES  12,692 / 40,000
Quanticade DarkNeutrino
fix-lmr-alpha-ttpv
search.c: Fix LMR ttpv alpha reduction
diff60.0+0.60
ELO    -2.88 +- 2.42 (95%)
LLR    -2.96 (-2.94, 2.94) [-3.00, 1.00]
GAMES  N: 17512 W: 3945 L: 4090 D: 9477
PENTA  [3, 2006, 4882, 1863, 2]
Integral Fury
tile_threat_accum
diff4.0+0.04
ELO    -7.90 +- 4.42 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 6948 W: 1685 L: 1843 D: 3420
PENTA  [76, 815, 1830, 697, 56]
Integral Fury
update_fmt
diff4.0+0.04
ELO    0.92 +- 4.48 (95%)
LLR    0.56 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 6054 W: 1607 L: 1591 D: 2856
PENTA  [37, 641, 1650, 667, 32]
Quanticade DarkNeutrino
simp-ttpv-cutnode
search.c: Simplify ttpv && cutnode adjustment
diff10.0+0.10
ELO    1.30 +- 2.16 (95%)
LLR    2.96 (-2.94, 2.94) [-3.00, 1.00]
GAMES  N: 24928 W: 5872 L: 5779 D: 13277
PENTA  [34, 2950, 6406, 3037, 37]
Quanticade DarkNeutrino
lmr-unreduce-on-pv
Unreduce on PV in LMR instead
diff60.0+0.60
ELO    -3.79 +- 2.87 (95%)
LLR    -2.96 (-2.94, 2.94) [-3.00, 1.00]
GAMES  N: 12922 W: 2893 L: 3034 D: 6995
PENTA  [1, 1550, 3500, 1409, 1]
Integral Fury
tile_threat_accum
diff4.0+0.04
ELO    -11.92 +- 5.29 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 4606 W: 1133 L: 1291 D: 2182
PENTA  [41, 573, 1218, 445, 26]