FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Active : 17 Machines / 512 Threads / 381.2 MNPS
Priority 0
Caissa Witek
singular-exact-margin
diff60.0+0.60
ELO    1.02 +- 1.58 (95%)
LLR    1.19 (-2.94, 2.94) [-0.50, 2.50]
GAMES  N: 44432 W: 10201 L: 10071 D: 24160
PENTA  [33, 5117, 11780, 5259, 27]
Illumina Mergener
history-aging
Refactor history
diff8.0+0.08
ELO    8.48 +- 13.69 (95%)
LLR    0.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 820 W: 199 L: 179 D: 442
PENTA  [6, 97, 188, 109, 10]
Quanticade DarkNeutrino
tuning
includes depths
smp diff20.0+0.20
TUNE   136 parameters
ITER   4,663 / 10,000
GAMES  18,654 / 40,000
Integral Fury
spsa
please ascend me!
smp diff20.0+0.20
TUNE   106 parameters
ITER   567 / 20,000
GAMES  2,268 / 80,000
Priority -1
Illumina Mergener
triangular-pv
diff8.0+0.08
ELO    1.21 +- 2.08 (95%)
LLR    2.37 (-2.25, 2.89) [-3.00, 0.00]
GAMES  N: 23274 W: 5148 L: 5067 D: 13059
PENTA  [95, 2107, 7158, 2176, 101]
Illumina Mergener
null-move-prefetch
Prefetching TT entries on NMP
diff8.0+0.08
ELO    1.21 +- 2.15 (95%)
LLR    0.61 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 24384 W: 5359 L: 5274 D: 13751
PENTA  [114, 2461, 6959, 2542, 116]
Illumina Mergener
no-eg-module
Remove endgame module
diff8.0+0.08
ELO    0.00 +- 0.00 (95%)
LLR    0.00 (-2.25, 2.89) [-3.00, 0.00]
GAMES  N: 0 W: 0 L: 0 D: 0
PENTA  [0, 0, 0, 0, 0]
Caissa Witek
singular-beta-history
diff10.0+0.10
ELO    -0.08 +- 1.23 (95%)
LLR    -1.57 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 81768 W: 19257 L: 19276 D: 43235
PENTA  [253, 9833, 20737, 9802, 259]
Caissa Witek
rfp-qsearch-verify
diff10.0+0.10
ELO    -0.07 +- 1.03 (95%)
LLR    -2.18 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 115766 W: 27204 L: 27227 D: 61335
PENTA  [354, 13909, 29379, 13888, 353]
Priority -2
Illumina Mergener
neg-extensions
Negative extensions
diff40.0+0.40
ELO    -6.89 +- 16.32 (95%)
LLR    -0.30 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 454 W: 87 L: 96 D: 271
PENTA  [2, 56, 119, 49, 1]
Illumina Mergener
neg-extensions
Negative extensions
diff8.0+0.08
ELO    -7.47 +- 9.30 (95%)
LLR    -1.04 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 1536 W: 320 L: 353 D: 863
PENTA  [7, 205, 380, 166, 10]
Illumina Mergener
fix-non-pawn-corrhist
Fix non pawn corrhist
diff8.0+0.08
ELO    -3.95 +- 5.40 (95%)
LLR    -1.51 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 3254 W: 683 L: 720 D: 1851
PENTA  [7, 321, 1010, 280, 9]
Finished
Quanticade Anematode
popbit
chud
diff4.0+0.04
ELO    2.07 +- 1.60 (95%)
LLR    2.99 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 46162 W: 11569 L: 11294 D: 23299
PENTA  [186, 4938, 12614, 5101, 242]
Quanticade Anematode
lmao
plz
diff4.0+0.04
ELO    4.36 +- 2.73 (95%)
LLR    2.91 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 17370 W: 4404 L: 4186 D: 8780
PENTA  [89, 1936, 4444, 2100, 116]
Integral Fury
vaporeon-300scale
Update tunables
diff10.0+0.10
ELO    -0.58 +- 1.88 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 34568 W: 8521 L: 8579 D: 17468
PENTA  [105, 4163, 8807, 4103, 106]
Clarity Vast
tune-concept
bored :þ
crash diff10.0+0.10
TUNE   56 parameters
ITER   505 / 10,000
GAMES  2,020 / 40,000
Integral Fury
300scale
diffN=20000
ELO    -13.49 +- 6.81 (95%)
LLR    -2.36 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 4330 W: 1239 L: 1407 D: 1684
PENTA  [120, 564, 943, 440, 98]
Integral Fury
vaporeon-300scale
Update tunables
diffN=20000
ELO    -0.13 +- 4.83 (95%)
LLR    -0.35 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8236 W: 2429 L: 2432 D: 3375
PENTA  [177, 997, 1777, 986, 181]
Integral Fury
tt_swar
diff4.0+0.04
ELO    -4.60 +- 5.16 (95%)
LLR    -1.15 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 4302 W: 1031 L: 1088 D: 2183
PENTA  [17, 490, 1196, 429, 19]
Integral Fury
tt_swar
diff4.0+0.04
ELO    -0.37 +- 6.42 (95%)
LLR    -0.16 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 2802 W: 704 L: 707 D: 1391
PENTA  [8, 304, 794, 273, 22]
Quanticade Anematode
prefetch-better
take 2
diff4.0+0.04
ELO    10.21 +- 4.43 (95%)
LLR    2.91 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6570 W: 1742 L: 1549 D: 3279
PENTA  [38, 655, 1717, 826, 49]
Illumina Mergener
better-improving-condition
Better improving condition
diff8.0+0.08
ELO    8.06 +- 4.87 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 5562 W: 1263 L: 1134 D: 3165
PENTA  [26, 624, 1350, 757, 24]
Quanticade DarkNeutrino
net59
net59 50% more training
diff60.0+0.60
ELO    4.03 +- 2.77 (95%)
LLR    2.39 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 14036 W: 3389 L: 3226 D: 7421
PENTA  [10, 1520, 3787, 1699, 2]
Illumina Mergener
qs-lmp
Qsearch late move pruning
diff8.0+0.08
ELO    -4.47 +- 4.99 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 4974 W: 1005 L: 1069 D: 2900
PENTA  [22, 607, 1293, 543, 22]
Quanticade DarkNeutrino
net59
Fixed nodes test to even check
diffN=5000
ELO    2.56 +- 2.03 (95%)
LLR    3.03 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 63902 W: 21698 L: 21227 D: 20977
PENTA  [2719, 6809, 12565, 6998, 2860]
Quanticade DarkNeutrino
net59
net59 50% more training
diff10.0+0.10
ELO    1.73 +- 2.43 (95%)
LLR    0.95 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 20542 W: 5107 L: 5005 D: 10430
PENTA  [65, 2391, 5252, 2503, 60]
Quanticade Anematode
more-hugepages
huge pages for worker data
diff4.0+0.04
ELO    -0.99 +- 2.14 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 26588 W: 6613 L: 6689 D: 13286
PENTA  [125, 3013, 7109, 2907, 140]