FuryBench

Finished
Pawnocchio SwedishChef	switch_movepicker	diff	10.0+0.10	ELO -1.32 +- 1.68 (95%) LLR -2.26 (-2.25, 2.89) [-3.00, 1.00] GAMES N: 43122 W: 10401 L: 10565 D: 22156 PENTA [136, 5217, 10988, 5115, 105]
Pawnocchio SwedishChef	bnfp_hist4	diff	10.0+0.10	ELO -0.76 +- 1.98 (95%) LLR -2.33 (-2.25, 2.89) [0.00, 3.00] GAMES N: 31462 W: 7657 L: 7726 D: 16079 PENTA [90, 3841, 7955, 3738, 107]
Pawnocchio SwedishChef	bnfp_hist3	diff	10.0+0.10	ELO 0.39 +- 0.99 (95%) LLR -2.28 (-2.25, 2.89) [0.00, 3.00] GAMES N: 125332 W: 30530 L: 30388 D: 64414 PENTA [357, 14916, 31996, 15022, 375]
Pawnocchio SwedishChef	write_prefetch2	smp diff	4.0+0.04	ELO -0.04 +- 1.44 (95%) LLR -2.28 (-2.25, 2.89) [0.00, 3.00] GAMES N: 58110 W: 14240 L: 14247 D: 29623 PENTA [182, 6883, 14924, 6892, 174]
Pawnocchio SwedishChef	switch_movepicker	diff	4.0+0.04	ELO -0.88 +- 2.09 (95%) LLR -2.31 (-2.25, 2.89) [0.00, 3.00] GAMES N: 29292 W: 7444 L: 7518 D: 14330 PENTA [198, 3286, 7746, 3224, 192]
Pawnocchio SwedishChef	write_prefetch	smp diff	4.0+0.04	ELO -6.39 +- 8.96 (95%) LLR -0.54 (-2.25, 2.89) [0.00, 3.00] GAMES N: 1576 W: 376 L: 405 D: 795 PENTA [10, 197, 395, 184, 2]
Pawnocchio SwedishChef	smp_tuned4	diff	40.0+0.40	ELO 1.01 +- 1.24 (95%) LLR 1.02 (-2.25, 2.89) [0.00, 3.00] GAMES N: 70856 W: 16753 L: 16547 D: 37556 PENTA [57, 8066, 18963, 8298, 44]
Vine SwedishChef	combined_v59_p21_test3	diff	10.0+0.10	ELO -6.16 +- 5.90 (95%) LLR -2.25 (-2.25, 2.89) [0.00, 5.00] GAMES N: 3946 W: 699 L: 769 D: 2478 PENTA [23, 515, 979, 421, 35]
Vine SwedishChef	combined_v59_p21_test2	diff	10.0+0.10	ELO -6.32 +- 5.97 (95%) LLR -2.25 (-2.25, 2.89) [0.00, 5.00] GAMES N: 3846 W: 722 L: 792 D: 2332 PENTA [33, 478, 964, 422, 26]
Pawnocchio SwedishChef	smp_tune4	crash smp diff	40.0+0.40	TUNE 315 parameters ITER 5,000 / 5,000 GAMES 40,000 / 40,000
Vine SwedishChef	smallnet_swish_swiglu_fr	diff	10.0+0.10	ELO -10.47 +- 7.47 (95%) LLR -2.29 (-2.25, 2.89) [0.00, 5.00] GAMES N: 2622 W: 548 L: 627 D: 1447 PENTA [29, 343, 640, 276, 23]
Pawnocchio SwedishChef	new_net_spsa_vals	diff	10.0+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]
Pawnocchio SwedishChef	mixed_data_sparser.nnue	diff	40.0+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	diff	10.0+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	diff	40.0+0.40	TUNE 298 parameters ITER 5,002 / 5,000 GAMES 40,016 / 40,000
Pawnocchio SwedishChef	mixed_data_sparser.nnue	diff	N=10000	ELO -2.40 +- 2.76 (95%) LLR -2.48 (-2.25, 2.89) [-3.00, 1.00] GAMES N: 33130 W: 11232 L: 11461 D: 10437 PENTA [1377, 3644, 6707, 3505, 1332]
Pawnocchio SwedishChef	new_net_spsa_1k	diff	10.0+0.10	ELO 4.34 +- 6.73 (95%) LLR 2.97 (-2.25, 2.89) [-10.00, 0.00] GAMES N: 2640 W: 652 L: 619 D: 1369 PENTA [3, 303, 683, 320, 11]
Pawnocchio SwedishChef	mixed_data_regularised_softer.nnue	diff	N=10000	ELO -1.65 +- 4.29 (95%) LLR -1.28 (-2.25, 2.89) [0.00, 3.00] GAMES N: 13886 W: 4707 L: 4773 D: 4406 PENTA [606, 1486, 2778, 1514, 559]
Pawnocchio SwedishChef	mixed_data_regularised_softer.nnue	diff	10.0+0.10	ELO -0.59 +- 4.45 (95%) LLR -0.42 (-2.25, 2.89) [0.00, 3.00] GAMES N: 6464 W: 1613 L: 1624 D: 3227 PENTA [21, 800, 1612, 767, 32]
Pawnocchio SwedishChef	new_net_spsa_2.5k	diff	40.0+0.40	ELO -12.32 +- 6.82 (95%) LLR -1.94 (-2.25, 2.89) [-3.00, 1.00] GAMES N: 2482 W: 546 L: 634 D: 1302 PENTA [4, 339, 642, 253, 3]
Pawnocchio SwedishChef	new_net_spsa	diff	40.0+0.40	TUNE 298 parameters ITER 2,560 / 5,000 GAMES 20,480 / 40,000
Pawnocchio SwedishChef	regularised	diff	10.0+0.10	ELO -1.20 +- 2.52 (95%) LLR -1.83 (-2.25, 2.89) [0.00, 3.00] GAMES N: 19098 W: 4644 L: 4710 D: 9744 PENTA [55, 2304, 4902, 2228, 60]
Pawnocchio SwedishChef	mixed_data_regularised.nnue	diff	10.0+0.10	ELO -6.55 +- 4.35 (95%) LLR -2.34 (-2.25, 2.89) [0.00, 3.00] GAMES N: 6742 W: 1636 L: 1763 D: 3343 PENTA [36, 861, 1692, 758, 24]
Pawnocchio SwedishChef	mixed_data_regularised.nnue	diff	N=10000	ELO -7.34 +- 4.79 (95%) LLR -3.15 (-2.25, 2.89) [0.00, 3.00] GAMES N: 11122 W: 3666 L: 3901 D: 3555 PENTA [500, 1230, 2280, 1107, 444]
Pawnocchio SwedishChef	conthist_cap_check	diff	40.0+0.40	ELO -5.80 +- 3.95 (95%) LLR -2.33 (-2.25, 2.89) [0.00, 3.00] GAMES N: 6954 W: 1580 L: 1696 D: 3678 PENTA [5, 856, 1866, 750, 0]

1 2 3 18 19 20 21 22 34 35 36

FuryBench Testing Framework