FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Pawnocchio SwedishChef
[Stormphrax] main~
diff40.0+0.40
ELO    38.26 +- 6.12 (95%)
GAMES  N: 2972/5000 W: 898 L: 572 D: 1502
PENTA  [0, 213, 740, 527, 6]
Pawnocchio SwedishChef
lde
diff10.0+0.10
ELO    -9.20 +- 4.86 (95%)
LLR    -2.46 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 5022 W: 1156 L: 1289 D: 2577
PENTA  [15, 657, 1293, 538, 8]
Pawnocchio SwedishChef
pretrained.nnue
diff40.0+0.40
ELO    2.16 +- 1.65 (95%)
LLR    2.95 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 40554 W: 9747 L: 9495 D: 21312
PENTA  [27, 4598, 10772, 4856, 24]
PlentyChess Yoshie2000
lmp-improving-beta
diff8.0+0.08
ELO    -1.32 +- 2.04 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 28124 W: 6835 L: 6942 D: 14347
PENTA  [48, 3412, 7239, 3325, 38]
Quanticade DarkNeutrino
selfgen
diffN=5000
ELO    0.02 +- 0.11 (95%)
GAMES  N: 30000156/30000000 W: 10809440 L: 10807378 D: 8383338
Integral Fury
allow_qs_tt_move
diff10.0+0.10
ELO    -4.09 +- 3.17 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 11734 W: 2825 L: 2963 D: 5946
PENTA  [27, 1450, 3057, 1300, 33]
Integral Fury
nmp_eval_beta_margin
diff10.0+0.10
ELO    -1.14 +- 1.94 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 31294 W: 7722 L: 7825 D: 15747
PENTA  [80, 3722, 8141, 3629, 75]
PlentyChess Yoshie2000
lmp-givescheck-again
diff8.0+0.08
ELO    0.09 +- 1.07 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 102632 W: 24942 L: 24914 D: 52776
PENTA  [176, 12187, 26565, 12209, 179]
PlentyChess Yoshie2000
lmp-givescheck-again-2
diff8.0+0.08
ELO    -0.62 +- 1.62 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 43934 W: 10639 L: 10717 D: 22578
PENTA  [77, 5205, 11473, 5143, 69]
Pawnocchio SwedishChef
pretrained.nnue
diff10.0+0.10
ELO    -0.30 +- 1.67 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 43378 W: 10424 L: 10462 D: 22492
PENTA  [150, 5132, 11127, 5166, 114]
Integral Fury
rolling_reductions
diff10.0+0.10
ELO    -1.73 +- 2.22 (95%)
LLR    -2.38 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 24860 W: 6194 L: 6318 D: 12348
PENTA  [87, 3010, 6341, 2924, 68]
Integral Fury
hindsight_worsening_again
diff10.0+0.10
ELO    -1.32 +- 2.07 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29254 W: 7176 L: 7287 D: 14791
PENTA  [102, 3596, 7334, 3501, 94]
Integral Fury
check_tt_cutoff_twice
diff10.0+0.10
ELO    -3.46 +- 3.00 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 13656 W: 3365 L: 3501 D: 6790
PENTA  [61, 1651, 3522, 1551, 43]
PlentyChess Yoshie2000
cj-probcut-guard
diff8.0+0.08
ELO    -0.06 +- 1.19 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 81274 W: 19702 L: 19715 D: 41857
PENTA  [116, 9690, 21057, 9639, 135]
Pawnocchio SwedishChef
shorter.nnue
diff10.0+0.10
ELO    -3.24 +- 3.26 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 11778 W: 2799 L: 2909 D: 6070
PENTA  [50, 1454, 2979, 1368, 38]