FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
PlentyChess Yoshie2000
lmr-rn-impcap
diff8.0+0.08
ELO    -1.04 +- 1.86 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 32842 W: 8015 L: 8113 D: 16714
PENTA  [52, 3855, 8703, 3761, 50]
PlentyChess Yoshie2000
lmr-overattacked
diff8.0+0.08
ELO    -2.14 +- 2.42 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 19604 W: 4700 L: 4821 D: 10083
PENTA  [33, 2367, 5117, 2258, 27]
PlentyChess Yoshie2000
promo-hash-bugfix
diff8.0+0.08
ELO    2.95 +- 1.95 (95%)
LLR    2.89 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29326 W: 7190 L: 6941 D: 15195
PENTA  [49, 3199, 7928, 3428, 59]
PlentyChess Yoshie2000
0126rrrr
diff8.0+0.08
ELO    -2.68 +- 2.64 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 16358 W: 3909 L: 4035 D: 8414
PENTA  [33, 1957, 4312, 1857, 20]
PlentyChess Yoshie2000
speedup-threatened
diff2.0+0.02
ELO    0.99 +- 2.09 (95%)
LLR    0.39 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 29794 W: 7512 L: 7427 D: 14855
PENTA  [200, 3305, 7819, 3356, 217]
PlentyChess Yoshie2000
more-policy
diff8.0+0.08
ELO    -2.48 +- 2.78 (95%)
LLR    -1.92 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 14862 W: 3554 L: 3660 D: 7648
PENTA  [25, 1791, 3904, 1687, 24]
Caissa Witek
tm_95
diff1.0+0.10
ELO    4.58 +- 2.39 (95%)
LLR    3.04 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 25654 W: 6673 L: 6335 D: 12646
PENTA  [230, 2944, 6160, 3244, 249]
Quanticade DarkNeutrino
rfp-depth
diff10.0+0.10
ELO    -1.14 +- 2.90 (95%)
LLR    -1.35 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 14636 W: 3398 L: 3446 D: 7792
PENTA  [46, 1795, 3675, 1765, 37]
Caissa Witek
master
diff10.0+0.10
ELO    6.86 +- 3.51 (95%)
GAMES  N: 10530/40000 W: 2632 L: 2424 D: 5474
PENTA  [34, 1219, 2566, 1397, 49]
PlentyChess Yoshie2000
threat-inputs-640
diff40.0+0.40
ELO    1.78 +- 1.37 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 58474 W: 14677 L: 14378 D: 29419
PENTA  [40, 6606, 15663, 6871, 57]
Caissa Yoshie2000
master
diff10.0+0.10
ELO    1.18 +- 2.51 (95%)
GAMES  N: 18836/40000 W: 4498 L: 4434 D: 9904
PENTA  [61, 2136, 4959, 2202, 60]
Schoenemann Jochen
feature/th-2
diff8.0+0.08
ELO    -2.44 +- 4.79 (95%)
LLR    -1.92 (-2.94, 2.94) [0.00, 5.00]
GAMES  N: 6974 W: 1759 L: 1808 D: 3407
PENTA  [90, 876, 1595, 845, 81]
Quanticade DarkNeutrino
lower-probcut
diff10.0+0.10
ELO    -4.93 +- 3.87 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8168 W: 1871 L: 1987 D: 4310
PENTA  [28, 1022, 2099, 908, 27]
PlentyChess Yoshie2000
threat-inputs-640
diff40.0+0.40
ELO    -6.77 +- 3.34 (95%)
GAMES  N: 10010/10000 W: 2418 L: 2613 D: 4979
PENTA  [11, 1250, 2686, 1039, 19]
Quanticade DarkNeutrino
tunable
crash diff80.0+0.80
TUNE   111 parameters
ITER   5,969 / 10,000
GAMES  95,504 / 160,000