FuryBench

FuryBench Testing Framework

Home to Integral, PlentyChess, Obsidian, Caissa, Quanticade, Serendipity, Spaghet, Schoenemann, Clarity, and Illumina

Finished
Fury	Vine	main	diff	N=1000	Generated 4000014/4000000 Games Elo: 0.01 +- 0.31 (95%) [N=4000000] Games: 4000014 W: 1629129 L: 1629034 D: 741851
Fury	Vine	material_scaling1	diff	10.0+0.10	LLR: -2.26 (-2.25, 2.89) [0.00, 5.00] Games: 4450 W: 1258 L: 1344 D: 1848 Ptnml(0-2): 153, 521, 923, 515, 113 Elo: -6.72 +- 7.02 (95%)
Fury	Vine	material_scaling1	diff	10.0+0.10	LLR: -2.35 (-2.25, 2.89) [0.00, 5.00] Games: 1914 W: 495 L: 598 D: 821 Ptnml(0-2): 78, 228, 415, 191, 45 Elo: -18.71 +- 10.74 (95%)
Fury	Vine	material_scaling1	diff	10.0+0.10	LLR: -2.30 (-2.25, 2.89) [0.00, 5.00] Games: 1224 W: 315 L: 420 D: 489 Ptnml(0-2): 53, 165, 252, 118, 24 Elo: -29.88 +- 13.49 (95%)
Fury	Vine	material_scaling	diff	10.0+0.10	LLR: -2.26 (-2.25, 2.89) [0.00, 5.00] Games: 7372 W: 2114 L: 2186 D: 3072 Ptnml(0-2): 240, 872, 1497, 874, 203 Elo: -3.39 +- 5.48 (95%)
Fury	Vine	policy_l2_concat	diff	10.0+0.10	LLR: -2.30 (-2.25, 2.89) [0.00, 5.00] Games: 462 W: 85 L: 200 D: 177 Ptnml(0-2): 31, 90, 74, 35, 1 Elo: -88.34 +- 22.49 (95%)
Fury	Vine	policy_l2_concat	diff	N=2000	LLR: -2.38 (-2.25, 2.89) [0.00, 5.00] Games: 2452 W: 945 L: 1072 D: 435 Ptnml(0-2): 207, 190, 511, 159, 159 Elo: -18.01 +- 11.85 (95%)
Fury	Vine	combined_v28_p8	diff	10.0+0.10	LLR: 2.90 (-2.25, 2.89) [0.00, 5.00] Games: 7302 W: 2360 L: 2179 D: 2763 Ptnml(0-2): 215, 827, 1472, 836, 301 Elo: 8.61 +- 5.69 (95%)
Fury	Vine	combined_v28_p8_test	diff	10.0+0.10	LLR: -2.53 (-2.25, 2.89) [0.00, 5.00] Games: 302 W: 20 L: 220 D: 62 Ptnml(0-2): 77, 48, 24, 2, 0 Elo: -276.84 +- 42.42 (95%)
Fury	Vine	div_cpuct	diff	40.0+0.40	LLR: -1.11 (-2.25, 2.89) [0.00, 5.00] Games: 1192 W: 298 L: 342 D: 552 Ptnml(0-2): 37, 140, 267, 134, 18 Elo: -12.83 +- 12.72 (95%)
Fury	Vine	div_cpuct	diff	10.0+0.10	LLR: -0.07 (-2.25, 2.89) [0.00, 5.00] Games: 1706 W: 512 L: 507 D: 687 Ptnml(0-2): 59, 192, 341, 207, 54 Elo: 1.02 +- 11.67 (95%)
Fury	Vine	variance_q_cpuct	diff	10.0+0.10	LLR: -2.32 (-2.25, 2.89) [0.00, 5.00] Games: 1298 W: 339 L: 446 D: 513 Ptnml(0-2): 54, 177, 272, 114, 32 Elo: -28.71 +- 13.20 (95%)
Fury	Vine	policy_entropy_cpuct	diff	10.0+0.10	LLR: -2.30 (-2.25, 2.89) [0.00, 5.00] Games: 618 W: 142 L: 263 D: 213 Ptnml(0-2): 41, 103, 113, 40, 12 Elo: -68.92 +- 20.43 (95%)
Fury	Vine	[Anura] main	diff	10.0+0.10	Elo: -34.33 +- 11.73 (95%) [N=2000] Games: 2000 W: 547 L: 744 D: 709 Ptnml(0-2): 109, 298, 343, 181, 69
Fury	Vine	combined_v26_p7_test	diff	10.0+0.10	LLR: 2.97 (-2.25, 2.89) [0.00, 5.00] Games: 8512 W: 2759 L: 2568 D: 3185 Ptnml(0-2): 286, 910, 1689, 1069, 302 Elo: 7.80 +- 5.27 (95%)
Fury	Vine	cpuct_visit_tweak	diff	40.0+0.40	LLR: -2.36 (-2.25, 2.89) [0.00, 5.00] Games: 4956 W: 1328 L: 1413 D: 2215 Ptnml(0-2): 126, 628, 1048, 557, 119 Elo: -5.96 +- 6.40 (95%)
Fury	Vine	cpuct_visit_tweak	diff	10.0+0.10	LLR: -0.79 (-2.25, 2.89) [0.00, 5.00] Games: 1342 W: 402 L: 434 D: 506 Ptnml(0-2): 44, 175, 265, 143, 44 Elo: -8.29 +- 13.17 (95%)
Fury	Vine	cpuct_visit_scaling	diff	40.0+0.40	LLR: 2.94 (-2.25, 2.89) [0.00, 5.00] Games: 928 W: 322 L: 173 D: 433 Ptnml(0-2): 8, 89, 168, 144, 55 Elo: 56.27 +- 15.92 (95%)
Fury	Vine	combined_v25_p6	diff	10.0+0.10	LLR: 2.92 (-2.25, 2.89) [0.00, 5.00] Games: 11846 W: 3181 L: 2986 D: 5679 Ptnml(0-2): 308, 1373, 2373, 1554, 315 Elo: 5.72 +- 4.23 (95%)
Fury	Vine	cpuct_visit_scaling	diff	10.0+0.10	LLR: 2.95 (-2.25, 2.89) [0.00, 5.00] Games: 6396 W: 1889 L: 1715 D: 2792 Ptnml(0-2): 149, 770, 1276, 764, 239 Elo: 9.45 +- 5.92 (95%)
Fury	Vine	combined_v25_p6_test1	diff	10.0+0.10	LLR: -2.34 (-2.25, 2.89) [0.00, 5.00] Games: 4566 W: 1227 L: 1318 D: 2021 Ptnml(0-2): 148, 591, 885, 522, 137 Elo: -6.93 +- 7.08 (95%)
Fury	Vine	combined_v25_p5	diff	10.0+0.10	LLR: 3.05 (-2.25, 2.89) [0.00, 5.00] Games: 2220 W: 685 L: 525 D: 1010 Ptnml(0-2): 51, 230, 415, 336, 78 Elo: 25.08 +- 10.07 (95%)
Fury	Vine	policy_512hl	diff	10.0+0.10	LLR: 2.97 (-2.25, 2.89) [0.00, 5.00] Games: 988 W: 346 L: 195 D: 447 Ptnml(0-2): 14, 76, 198, 157, 49 Elo: 53.52 +- 14.93 (95%)
Fury	Vine	combined_v25_p4_test	diff	10.0+0.10	LLR: -2.43 (-2.25, 2.89) [0.00, 5.00] Games: 4666 W: 1227 L: 1322 D: 2117 Ptnml(0-2): 161, 594, 883, 569, 126 Elo: -7.07 +- 7.02 (95%)
Fury	Vine	combined_v25_p3	diff	10.0+0.10	LLR: 3.01 (-2.25, 2.89) [0.00, 5.00] Games: 2632 W: 862 L: 698 D: 1072 Ptnml(0-2): 73, 269, 500, 369, 105 Elo: 21.68 +- 9.50 (95%)

1 2 3 14 15 16