FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Caissa Witek
eval_scale_192
diff8.0+0.08
ELO    -2.54 +- 2.05 (95%)
LLR    -2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 30450 W: 7156 L: 7379 D: 15915
PENTA  [163, 3718, 7622, 3623, 99]
Pawnocchio SwedishChef
512_testnet_vine_01_11.nnue
diff40.0+0.40
ELO    10.37 +- 4.35 (95%)
LLR    2.96 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6334 W: 1721 L: 1532 D: 3081
PENTA  [13, 676, 1599, 867, 12]
Caissa Witek
lmr_root
diff10.0+0.10
ELO    -0.66 +- 1.47 (95%)
LLR    -2.18 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 58260 W: 13710 L: 13820 D: 30730
PENTA  [231, 7039, 14688, 6953, 219]
Caissa Witek
master
diff1.0+0.00
ELO    2.76 +- 4.20 (95%)
GAMES  N: 10056/40000 W: 2141 L: 2061 D: 5854
PENTA  [173, 1184, 2243, 1246, 182]
Caissa Witek
master
diff10.0+0.10
ELO    5.00 +- 2.54 (95%)
GAMES  N: 20450/40000 W: 5046 L: 4752 D: 10652
PENTA  [82, 2412, 4968, 2656, 107]
Pawnocchio SwedishChef
2048pw
diffN=10000
ELO    12.98 +- 5.76 (95%)
LLR    3.07 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 7740 W: 2801 L: 2512 D: 2427
PENTA  [287, 752, 1600, 847, 384]
Pawnocchio SwedishChef
2048hl_scaled
diff10.0+0.10
ELO    -7.00 +- 5.67 (95%)
LLR    -1.43 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 3822 W: 869 L: 946 D: 2007
PENTA  [10, 506, 955, 431, 9]
Caissa Witek
master
diff40.0+0.40
ELO    1.31 +- 2.35 (95%)
GAMES  N: 20948/40000 W: 4842 L: 4763 D: 11343
PENTA  [25, 2469, 5411, 2540, 29]
Pawnocchio SwedishChef
2048hl_scaled
diff40.0+0.40
ELO    -4.16 +- 4.26 (95%)
LLR    -1.53 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6174 W: 1421 L: 1495 D: 3258
PENTA  [6, 760, 1627, 690, 4]
Pawnocchio SwedishChef
2048hl_scaled
diffN=20000
ELO    6.33 +- 6.79 (95%)
GAMES  N: 4774/10000 W: 1580 L: 1493 D: 1701
PENTA  [139, 521, 992, 584, 151]
Caissa Witek
eval-68-29B
frc diff10.0+0.10
ELO    4.23 +- 2.21 (95%)
LLR    2.96 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 24306 W: 4361 L: 4065 D: 15880
PENTA  [143, 2380, 6826, 2646, 158]
Vine SwedishChef
combined_v57_p20_test4
diff10.0+0.10
ELO    -5.83 +- 5.95 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 4290 W: 929 L: 1001 D: 2360
PENTA  [41, 568, 1005, 484, 47]
Caissa Witek
eval-68-29B
diff10.0+0.10
ELO    3.67 +- 2.07 (95%)
LLR    2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 29320 W: 7107 L: 6797 D: 15416
PENTA  [92, 3418, 7344, 3700, 106]
Pawnocchio SwedishChef
history_refactor
diff10.0+0.10
ELO    1.16 +- 2.07 (95%)
LLR    2.94 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 26628 W: 6332 L: 6243 D: 14053
PENTA  [36, 3099, 6956, 3186, 37]
Pawnocchio SwedishChef
mixed_data_d2z_s1.nnue
diff10.0+0.10
ELO    -1.02 +- 3.34 (95%)
LLR    -0.92 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 10532 W: 2507 L: 2538 D: 5487
PENTA  [21, 1264, 2727, 1233, 21]