FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Caissa Witek
log_exact_only
diff8.0+0.08
ELO    1.38 +- 1.22 (95%)
LLR    2.30 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 82812 W: 20001 L: 19673 D: 43138
PENTA  [316, 9499, 21467, 9789, 335]
PlentyChess Yoshie2000
noisy-text
diff8.0+0.08
ELO    -2.31 +- 2.52 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 18630 W: 4438 L: 4562 D: 9630
PENTA  [41, 2278, 4790, 2176, 30]
PlentyChess Yoshie2000
frac-lmr-imp
diff8.0+0.08
ELO    -2.68 +- 2.66 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 16436 W: 3937 L: 4064 D: 8435
PENTA  [21, 2025, 4262, 1880, 30]
PlentyChess Yoshie2000
frac-lmr-cond
diff8.0+0.08
ELO    -3.64 +- 2.99 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 12808 W: 3020 L: 3154 D: 6634
PENTA  [20, 1566, 3368, 1428, 22]
Caissa Witek
cont_hist_scale_down
diff10.0+0.10
ELO    -2.57 +- 2.02 (95%)
LLR    -2.96 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 29660 W: 6929 L: 7148 D: 15583
PENTA  [111, 3575, 7648, 3414, 82]
PlentyChess Yoshie2000
main
diff40.0+0.40
ELO    10.42 +- 3.28 (95%)
GAMES  N: 10004/10000 W: 2624 L: 2324 D: 5056
PENTA  [2, 1012, 2674, 1312, 2]
PlentyChess Yoshie2000
red-fds-red
diff8.0+0.08
ELO    -1.28 +- 2.00 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29368 W: 7117 L: 7225 D: 15026
PENTA  [55, 3557, 7564, 3457, 51]
PlentyChess Yoshie2000
qs-hist-bonus
diff8.0+0.08
ELO    -0.18 +- 1.30 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 68404 W: 16663 L: 16698 D: 35043
PENTA  [113, 8049, 17904, 8032, 104]
PlentyChess Yoshie2000
tt-dext-depth-inc
diff8.0+0.08
ELO    -0.71 +- 1.67 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 40634 W: 9777 L: 9860 D: 20997
PENTA  [58, 4771, 10734, 4704, 50]
Pawnocchio SwedishChef
mixed_data_chonked_properly.nnue
diff40.0+0.40
ELO    1.64 +- 1.32 (95%)
LLR    2.92 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 64212 W: 15566 L: 15263 D: 33383
PENTA  [66, 7366, 16944, 7659, 71]
Caissa Witek
eval-72-266B
diff60.0+0.60
ELO    -0.30 +- 1.55 (95%)
LLR    -2.39 (-2.94, 2.94) [0.00, 3.00]
GAMES  N: 45620 W: 10253 L: 10292 D: 25075
PENTA  [23, 5327, 12157, 5272, 31]
Quanticade DarkNeutrino
selfgen
diffN=5000
ELO    0.05 +- 0.10 (95%)
GAMES  N: 30000106/30000000 W: 9605905 L: 9601588 D: 10792613
PlentyChess Yoshie2000
impcap-more-ext
diff8.0+0.08
ELO    0.03 +- 1.12 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 92090 W: 22472 L: 22463 D: 47155
PENTA  [161, 10812, 24088, 10825, 159]
PlentyChess Yoshie2000
pv-corr-ext
diff8.0+0.08
ELO    -0.07 +- 1.19 (95%)
LLR    -2.34 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 81348 W: 19811 L: 19827 D: 41710
PENTA  [140, 9577, 21249, 9575, 133]
Obsidian Yoshie2000
[PlentyChess] 0146r
diffN=20000
ELO    -46.52 +- 10.12 (95%)
GAMES  N: 2066/2000 W: 500 L: 775 D: 791
PENTA  [91, 317, 435, 156, 34]