FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Caissa Witek
14_king_buckets
diff10.0+0.10
ELO    4.66 +- 1.97 (95%)
LLR    2.97 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 14400 W: 2758 L: 2565 D: 9077
PENTA  [1, 764, 5478, 955, 2]
Caissa Witek
14_king_buckets
diff10.0+0.10
ELO    1.16 +- 2.58 (95%)
LLR    0.38 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 18312 W: 4333 L: 4272 D: 9707
PENTA  [52, 2153, 4692, 2200, 59]
Quanticade DarkNeutrino
net8
diff10.0+0.10
ELO    -9.91 +- 7.48 (95%)
LLR    -1.45 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 3506 W: 961 L: 1061 D: 1484
PENTA  [76, 480, 749, 364, 84]
Clarity Vast
rw-tt-staticeval
diff8.0+0.08
ELO    -8.18 +- 6.79 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 3270 W: 710 L: 787 D: 1773
PENTA  [32, 446, 752, 377, 28]
Clarity Vast
rw-tt-staticeval
diff8.0+0.08
ELO    -5.29 +- 5.63 (95%)
LLR    -2.35 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 4864 W: 1120 L: 1194 D: 2550
PENTA  [52, 637, 1128, 563, 52]
Quanticade DarkNeutrino
net7
diff10.0+0.10
ELO    67.83 +- 13.30 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 1302 W: 545 L: 294 D: 463
PENTA  [16, 89, 254, 212, 80]
Pawnocchio SwedishChef
new_net_spsa_vals
diff10.0+0.10
ELO    7.42 +- 3.67 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8948 W: 2221 L: 2030 D: 4697
PENTA  [21, 977, 2293, 1156, 27]
Quanticade DarkNeutrino
net6
diff10.0+0.10
ELO    28.92 +- 8.84 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 2998 W: 1126 L: 877 D: 995
PENTA  [74, 275, 620, 388, 142]
PlentyChess Yoshie2000
reverse-qs-3
diff40.0+0.40
ELO    -0.16 +- 1.21 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 69250 W: 17303 L: 17335 D: 34612
PENTA  [14, 7482, 19659, 7462, 8]
Quanticade DarkNeutrino
net5
diff10.0+0.10
ELO    -408.10 +- 10.88 (95%)
GAMES  N: 5004/5000 W: 17 L: 4149 D: 838
PENTA  [1653, 826, 23, 0, 0]
Quanticade DarkNeutrino
net5
diff60.0+0.60
ELO    39.54 +- 19.31 (95%)
LLR    0.78 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 556 W: 201 L: 138 D: 217
PENTA  [8, 51, 108, 92, 19]
Quanticade DarkNeutrino
net5
diff10.0+0.10
ELO    53.78 +- 11.57 (95%)
LLR    2.99 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 1654 W: 663 L: 409 D: 582
PENTA  [28, 122, 322, 278, 77]
Pawnocchio SwedishChef
mixed_data_sparser.nnue
diff40.0+0.40
ELO    -2.23 +- 2.72 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 15136 W: 3591 L: 3688 D: 7857
PENTA  [20, 1801, 4015, 1720, 12]
Pawnocchio SwedishChef
mixed_data_sparser.nnue
diff10.0+0.10
ELO    -1.13 +- 2.26 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 24950 W: 6129 L: 6210 D: 12611
PENTA  [90, 3106, 6175, 3003, 101]
Pawnocchio SwedishChef
new_net_spsa
diff40.0+0.40
TUNE   298 parameters
ITER   5,002 / 5,000
GAMES  40,016 / 40,000