FuryBench

Finished
Vine SwedishChef	smallnet_swish_swiglu_swish	diff	N=10000	ELO -18.43 +- 9.88 (95%) LLR -2.59 (-2.25, 2.89) [0.00, 5.00] GAMES N: 2076 W: 465 L: 575 D: 1036 PENTA [49, 319, 406, 221, 43]
Vine SwedishChef	smallnet_swishglu_proper_half	diff	10.0+0.10	ELO -3.25 +- 4.79 (95%) LLR -2.27 (-2.25, 2.89) [0.00, 5.00] GAMES N: 6744 W: 1502 L: 1565 D: 3677 PENTA [88, 826, 1587, 803, 68]
Vine SwedishChef	smallnet_swishglu_half_proper	diff	10.0+0.10	ELO -1.00 +- 3.51 (95%) LLR -2.29 (-2.25, 2.89) [0.00, 5.00] GAMES N: 13160 W: 3058 L: 3096 D: 7006 PENTA [174, 1610, 3058, 1556, 182]
Vine SwedishChef	smallnet_swishglu_proper_noapprox	crash diff	N=10000	ELO 1.46 +- 2.68 (95%) LLR 0.04 (-2.25, 2.89) [0.00, 5.00] GAMES N: 21352 W: 4958 L: 4868 D: 11526 PENTA [253, 2436, 5243, 2456, 288]
Vine SwedishChef	smallnet_swishglu_proper	diff	10.0+0.10	ELO -22.62 +- 10.48 (95%) LLR -2.29 (-2.25, 2.89) [0.00, 5.00] GAMES N: 1292 W: 213 L: 297 D: 782 PENTA [14, 191, 315, 117, 9]
Vine SwedishChef	smallnet_swishglu_proper	diff	N=10000	ELO -29.22 +- 12.60 (95%) LLR -2.34 (-2.25, 2.89) [0.00, 5.00] GAMES N: 1168 W: 223 L: 321 D: 624 PENTA [34, 169, 256, 111, 14]
Vine SwedishChef	smallnet_swish_l2	diff	10.0+0.10	ELO 1.25 +- 5.93 (95%) LLR -0.08 (-2.25, 2.89) [0.00, 5.00] GAMES N: 4736 W: 1125 L: 1108 D: 2503 PENTA [58, 593, 1066, 576, 75]
Vine SwedishChef	smallnet_swish_swiglu	diff	10.0+0.10	ELO 5.32 +- 3.89 (95%) LLR 2.91 (-2.25, 2.89) [0.00, 5.00] GAMES N: 11112 W: 2767 L: 2597 D: 5748 PENTA [166, 1267, 2523, 1431, 169]
Vine SwedishChef	smallnet_swish_swiglu	diff	N=10000	ELO 11.02 +- 6.20 (95%) LLR 3.06 (-2.25, 2.89) [0.00, 5.00] GAMES N: 5140 W: 1467 L: 1304 D: 2369 PENTA [104, 576, 1070, 693, 127]
Vine SwedishChef	smallnet_dual_swiglu	diff	N=10000	ELO 0.40 +- 2.53 (95%) LLR -2.25 (-2.25, 2.89) [0.00, 5.00] GAMES N: 29218 W: 7368 L: 7334 D: 14516 PENTA [552, 3615, 6278, 3575, 589]
Vine SwedishChef	combined_v58_p21_test1	diff	10.0+0.10	ELO -2.32 +- 4.19 (95%) LLR -2.27 (-2.25, 2.89) [0.00, 5.00] GAMES N: 8222 W: 1724 L: 1779 D: 4719 PENTA [87, 982, 2007, 969, 66]
Vine SwedishChef	smallnet_dual_swish	diff	10.0+0.10	ELO 14.01 +- 7.14 (95%) LLR 2.90 (-2.25, 2.89) [0.00, 5.00] GAMES N: 3474 W: 886 L: 746 D: 1842 PENTA [42, 395, 755, 471, 74]
Vine SwedishChef	combined_v58_p21_test1	diff	N=10000	ELO -9.20 +- 7.62 (95%) LLR -2.30 (-2.25, 2.89) [0.00, 5.00] GAMES N: 3288 W: 822 L: 909 D: 1557 PENTA [78, 434, 680, 401, 51]
Pawnocchio SwedishChef	mixed_data_dualact_3.nnue	diff	40.0+0.40	ELO -2.82 +- 2.94 (95%) LLR -2.26 (-2.25, 2.89) [0.00, 3.00] GAMES N: 12306 W: 2881 L: 2981 D: 6444 PENTA [7, 1436, 3365, 1340, 5]
Pawnocchio SwedishChef	mixed_data_dualact_3.nnue	diff	10.0+0.10	ELO -3.10 +- 5.17 (95%) LLR -0.83 (-2.25, 2.89) [0.00, 3.00] GAMES N: 4374 W: 1023 L: 1062 D: 2289 PENTA [15, 519, 1150, 496, 7]
Pawnocchio SwedishChef	mixed_data_dualact_2.nnue	diff	40.0+0.40	ELO -7.15 +- 5.40 (95%) LLR -1.58 (-2.25, 2.89) [0.00, 3.00] GAMES N: 4084 W: 911 L: 995 D: 2178 PENTA [4, 552, 1012, 472, 2]
Pawnocchio SwedishChef	mixed_data_dualact_2.nnue	diff	10.0+0.10	ELO -2.27 +- 2.82 (95%) LLR -2.27 (-2.25, 2.89) [0.00, 3.00] GAMES N: 15428 W: 3737 L: 3838 D: 7853 PENTA [35, 1937, 3881, 1816, 45]
Pawnocchio SwedishChef	dualact_l2	diff	10.0+0.10	ELO -0.04 +- 2.68 (95%) LLR -0.64 (-2.25, 2.89) [0.00, 3.00] GAMES N: 16384 W: 3972 L: 3974 D: 8438 PENTA [44, 1915, 4271, 1923, 39]
Pawnocchio SwedishChef	dualact_l2	diff	N=10000	ELO 0.50 +- 2.69 (95%) LLR -0.70 (-2.25, 2.89) [0.00, 3.00] GAMES N: 34622 W: 11842 L: 11792 D: 10988 PENTA [1430, 3632, 7114, 3728, 1407]
Pawnocchio SwedishChef	mixed_data_dualact_ranger.nnue	diff	10.0+0.10	ELO -25.55 +- 11.32 (95%) LLR -1.20 (-2.25, 2.89) [0.00, 3.00] GAMES N: 940 W: 192 L: 261 D: 487 PENTA [5, 143, 239, 82, 1]
Pawnocchio SwedishChef	mixed_data_dualact_ranger.nnue	diff	N=10000	ELO -12.28 +- 6.55 (95%) LLR -2.72 (-2.25, 2.89) [0.00, 3.00] GAMES N: 6142 W: 2028 L: 2245 D: 1869 PENTA [321, 659, 1236, 626, 229]
Pawnocchio SwedishChef	dualact	diff	40.0+0.40	ELO 6.27 +- 3.29 (95%) LLR 2.89 (-2.25, 2.89) [0.00, 3.00] GAMES N: 10364 W: 2563 L: 2376 D: 5425 PENTA [6, 1137, 2711, 1320, 8]
Pawnocchio SwedishChef	nnz	diff	4.0+0.04	ELO 10.18 +- 4.38 (95%) LLR 2.94 (-2.25, 2.89) [0.00, 3.00] GAMES N: 6590 W: 1729 L: 1536 D: 3325 PENTA [32, 669, 1708, 846, 40]
Pawnocchio SwedishChef	dualact	diff	10.0+0.10	ELO 8.54 +- 3.97 (95%) LLR 2.90 (-2.25, 2.89) [0.00, 3.00] GAMES N: 7690 W: 1967 L: 1778 D: 3945 PENTA [21, 831, 1952, 1020, 21]
Pawnocchio SwedishChef	dualact	diff	N=10000	ELO 7.78 +- 4.43 (95%) LLR 2.89 (-2.25, 2.89) [0.00, 3.00] GAMES N: 12904 W: 4569 L: 4280 D: 4055 PENTA [496, 1308, 2645, 1417, 586]

1 2 3 21 22 23 24 25 34 35 36

FuryBench Testing Framework