FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Caissa Witek
corrhist_cycle_draw
diff40.0+0.40
ELO    1.03 +- 1.54 (95%)
LLR    0.71 (-2.94, 2.94) [0.00, 3.00]
GAMES  N: 48006 W: 11119 L: 10976 D: 25911
PENTA  [52, 5596, 12559, 5749, 47]
Caissa Witek
corrhist_cycle_draw
diff10.0+0.10
ELO    0.29 +- 0.61 (95%)
LLR    -2.39 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 331236 W: 78634 L: 78356 D: 174246
PENTA  [1175, 39529, 83757, 40157, 1000]
Integral Fury
ti-vf-768
diffN=20000
ELO    -63.56 +- 13.65 (95%)
LLR    -2.31 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 1310 W: 314 L: 551 D: 445
PENTA  [88, 192, 266, 87, 22]
Clarity Vast
bestmove
Get best move from PV table I expect null moves, which I'll fix later (hopefully later today)
crash diff8.0+0.08
ELO    4.35 +- 3.68 (95%)
LLR    2.95 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 9754 W: 2332 L: 2210 D: 5212
PENTA  [55, 1104, 2444, 1212, 62]
Integral Fury
aggressive_policy_with_ti
diff10.0+0.10
ELO    -10.12 +- 4.79 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 5222 W: 1254 L: 1406 D: 2562
PENTA  [19, 678, 1368, 528, 18]
Caissa Witek
fix-bmi2
Fix pext/pdep and MulHi64 falling back to software on non-Windows builds Also, with pext working, restore -DUSE_BMI2 in the makefile native probe. No functional change.
diff5.0+0.05
ELO    3.01 +- 1.84 (95%)
LLR    2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 37274 W: 9297 L: 8974 D: 19003
PENTA  [203, 4093, 9721, 4418, 202]
Integral Fury
ti-vf-768
diffN=20000
ELO    -21.25 +- 9.23 (95%)
LLR    -2.43 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 2374 W: 650 L: 795 D: 929
PENTA  [67, 338, 508, 221, 53]
Integral Fury
[Obsidian] main
diff40.0+0.40
ELO    -27.00 +- 5.04 (95%)
GAMES  N: 5002/5000 W: 1083 L: 1471 D: 2448
PENTA  [37, 781, 1223, 453, 7]
Quanticade DarkNeutrino
net58
1024L1 with 50% more SBs on both stages compared to master
crash smp diff16.0+0.16
ELO    -1.52 +- 3.62 (95%)
LLR    -0.93 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8000 W: 1864 L: 1899 D: 4237
PENTA  [3, 912, 2204, 879, 2]
Integral Fury
lmp_hist
diff10.0+0.10
ELO    -1.17 +- 1.98 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 30656 W: 7612 L: 7715 D: 15329
PENTA  [81, 3679, 7913, 3572, 83]
Integral Fury
aggressive_policy_with_ti
diff10.0+0.10
ELO    -9.68 +- 4.79 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 5492 W: 1304 L: 1457 D: 2731
PENTA  [29, 726, 1372, 607, 12]
Integral Fury
lmp_hist
diff10.0+0.10
ELO    -0.96 +- 1.97 (95%)
LLR    -2.03 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 31458 W: 7840 L: 7927 D: 15691
PENTA  [96, 3802, 8015, 3725, 91]
Integral Fury
qs_see_catchup
diff10.0+0.10
ELO    -2.49 +- 2.57 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 17982 W: 4399 L: 4528 D: 9055
PENTA  [47, 2179, 4663, 2060, 42]
Caissa Witek
avxvnni_no_bmi2
AVX-VNNI support
diff5.0+0.05
ELO    3.86 +- 2.15 (95%)
LLR    2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 28568 W: 7166 L: 6849 D: 14553
PENTA  [148, 3252, 7222, 3459, 203]
Integral Fury
qs_see_catchup
diff10.0+0.10
ELO    -21.78 +- 6.74 (95%)
LLR    -2.34 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 2556 W: 568 L: 728 D: 1260
PENTA  [8, 379, 659, 229, 3]