OpenBench

OpenBench Testing Framework

Active : 1 Machines / 240 Threads / 132.66 MNPS
Priority 0
Rosent	Winter	qnet_382_d32 *	diff	8.0+0.08	LLR: 1.58 (-2.94, 2.94) [0.00, 5.00] Games: 13492 W: 3379 L: 3244 D: 6869 Ptnml(0-2): 303, 1589, 2825, 1728, 301	Even larger quantized net. Might not yet be sufficiently mature.
Vshche	Igel	static_tt_eval	diff	60.0+0.60	LLR: 1.09 (-2.94, 2.94) [0.00, 2.00] Games: 42888 W: 10039 L: 9883 D: 22966 Ptnml(0-2): 50, 5053, 11071, 5231, 39	3.7.4: store static evaluation in TT
Jhonno	Berserk	[Stockfish] dev	diff	N=5000 *	Generated 10445688/16666667 Games Elo: -20.21 +- 0.19 (95%) [N=16666667] Games: 10445688 W: 3974389 L: 4581241 D: 1890058
Priority -1
Rosent	Winter	net382_d24f64b *	diff	8.0+0.08	LLR: 0.79 (-2.94, 2.94) [0.00, 5.00] Games: 9980 W: 2443 L: 2362 D: 5175 Ptnml(0-2): 212, 1170, 2133, 1275, 200	Added net definition
Priority -5
Terje	Weiss	Connectivity2	diff	60.0+0.60	LLR: -1.17 (-2.94, 2.94) [0.00, 3.00] Games: 49430 W: 12731 L: 12689 D: 24010 Ptnml(0-2): 339, 5894, 12200, 5950, 332

Finished
Rosent	Winter	qnet_382_d24 *	diff	40.0+0.40	LLR: 2.95 (-2.94, 2.94) [0.00, 5.00] Games: 3404 W: 749 L: 622 D: 2033 Ptnml(0-2): 28, 331, 873, 426, 44	Now that net is quantized, we try the larger size again.
Andrew	Ethereal	master	diff	10.0+0.10	LLR: 0.00 (-2.94, 2.94) [0.00, 3.00] Games: 0 W: 0 L: 0 D: 0 Ptnml(0-2): 0, 0, 0, 0, 0	fake
Andrew	Ethereal	master	diff	10.0+0.10	LLR: 0.00 (-2.94, 2.94) [0.00, 3.00] Games: 0 W: 0 L: 0 D: 0 Ptnml(0-2): 0, 0, 0, 0, 0	fake
Rosent	Winter	qnet_382_d24 *	diff	8.0+0.08	LLR: 2.96 (-2.94, 2.94) [0.00, 5.00] Games: 12870 W: 3262 L: 3070 D: 6538 Ptnml(0-2): 265, 1499, 2728, 1665, 278	Now that net is quantized, we try the larger size again.
Jhonno	Berserk	[Stockfish] dev	diff	N=5000 *	Generated 15974304/33333333 Games Elo: -20.27 +- 0.15 (95%) [N=33333333] Games: 15974304 W: 6074897 L: 7005773 D: 2893634
Rosent	Winter	quantize_net *	diff	40.0+0.40	LLR: 2.96 (-2.94, 2.94) [0.00, 5.00] Games: 1382 W: 324 L: 201 D: 857 Ptnml(0-2): 7, 121, 325, 218, 20	Quantized network. Should be faster, at the cost of a little accuracy.
Rosent	Winter	quantize_net *	diff	8.0+0.08	LLR: 2.97 (-2.94, 2.94) [0.00, 5.00] Games: 1012 W: 301 L: 160 D: 551 Ptnml(0-2): 10, 80, 211, 169, 36	Quantized network. Should be faster, at the cost of a little accuracy.
Rosent	Winter	net382_W50a *	diff	8.0+0.08	LLR: -2.96 (-2.94, 2.94) [0.00, 5.00] Games: 4510 W: 1066 L: 1178 D: 2266 Ptnml(0-2): 109, 580, 971, 504, 91	Net trained with more uniform data. If this is not negative we are happy because it simplifies our life. If this is negative it is fine as it means we were doing something reasonably fine.
Vshche	Igel	static_tt_eval	diff	5.0+0.05	LLR: 0.24 (-2.94, 2.94) [0.00, 2.00] Games: 192 W: 57 L: 35 D: 100 Ptnml(0-2): 0, 16, 42, 38, 0	3.7.4: store static evaluation in TT
Vshche	Igel	static_tt_eval	diff	5.0+0.05	LLR: 2.96 (-2.94, 2.94) [0.00, 2.00] Games: 4524 W: 1273 L: 997 D: 2254 Ptnml(0-2): 12, 424, 1116, 696, 14	3.7.4: store static evaluation in TT
Vshche	Igel	static_tt_eval	diff	10.0+0.10	LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 12652 W: 3161 L: 2871 D: 6620 Ptnml(0-2): 55, 1396, 3129, 1696, 50	3.7.4: store static evaluation in TT
Vshche	Igel	draw_take2	diff	10.0+0.10	LLR: -2.71 (-2.94, 2.94) [0.00, 2.00] Games: 51760 W: 12076 L: 12242 D: 27442 Ptnml(0-2): 217, 6090, 13410, 5968, 195	3.7.3: yet another draw detection fix
Jhonno	Berserk	[Stockfish] dev	diff	N=7500 *	Generated 10000996/10000000 Games Elo: -9.47 +- 0.19 (95%) [N=10000000] Games: 10000996 W: 3924158 L: 4196621 D: 1880217
Vshche	Igel	jitter2	diff	10.0+0.10	LLR: -1.92 (-2.94, 2.94) [0.00, 2.00] Games: 84208 W: 15919 L: 15951 D: 52338 Ptnml(0-2): 14, 5168, 31774, 5132, 16	3.7.3: jitter draws - after rebase
Vshche	Igel	draw_take2	diff	10.0+0.10	LLR: 2.97 (-2.94, 2.94) [-3.00, 1.00] Games: 28970 W: 6894 L: 6803 D: 15273 Ptnml(0-2): 109, 3421, 7361, 3458, 136	3.7.3: yet another draw detection fix
Vshche	Igel	incheck	diff	10.0+0.10	LLR: -2.34 (-2.94, 2.94) [0.00, 2.00] Games: 29350 W: 6983 L: 7151 D: 15216 Ptnml(0-2): 122, 3606, 7378, 3456, 113	3.7.3: improve incheck condition
Vshche	Igel	razoring	diff	10.0+0.10	LLR: -2.96 (-2.94, 2.94) [0.00, 2.00] Games: 82576 W: 19850 L: 19995 D: 42731 Ptnml(0-2): 373, 10030, 20588, 9963, 334	3.7.3: allow razoring for null moves
Andrew	Berserk	[Stockfish] dev	diff	N=7500 *	Generated 32708/10000000 Games Elo: 1.04 +- 3.21 (95%) [N=10000000] Games: 32708 W: 11917 L: 11819 D: 8972	Mirrors 40853 -- with stacksize fix?
Jhonno	Berserk	[Stockfish] dev	diff	N=7500 *	Generated 61646/10000000 Games Elo: 1.05 +- 2.34 (95%) [N=10000000] Games: 61646 W: 22601 L: 22414 D: 16631
Vshche	Igel	razoring	diff	60.0+0.60	LLR: 0.04 (-2.94, 2.94) [0.00, 2.00] Games: 3962 W: 916 L: 907 D: 2139 Ptnml(0-2): 2, 446, 1075, 457, 1	3.7.3: allow razoring for null moves
Vshche	Igel	ep-take2	diff	10.0+0.10	LLR: 2.99 (-2.94, 2.94) [-3.00, 1.00] Games: 140020 W: 33463 L: 33537 D: 73020 Ptnml(0-2): 557, 16389, 36185, 16329, 550	3.7.2: handle enpassants with tb
Vshche	Igel	ext-take2	diff	10.0+0.10	LLR: 0.01 (-2.94, 2.94) [0.00, 2.00] Games: 108116 W: 26102 L: 25937 D: 56077 Ptnml(0-2): 453, 13144, 26696, 13315, 450	3.7.2: reduce extensions
Vshche	Igel	jitter	diff	10.0+0.10	LLR: 0.23 (-2.94, 2.94) [0.00, 2.00] Games: 90770 W: 17068 L: 16963 D: 56739 Ptnml(0-2): 17, 5396, 34449, 5511, 12	3.7.2: jitter draws - Endgames.epd
Vshche	Igel	jitter	diff	10.0+0.10	LLR: -0.84 (-2.94, 2.94) [0.00, 2.00] Games: 42774 W: 10104 L: 10116 D: 22554 Ptnml(0-2): 172, 4992, 11048, 5026, 149	3.7.2: jitter draws - UHO_Lichess_4852_v1.epd
Jhonno	Berserk	[Stockfish] dev	diff	N=5000 *	Generated 9911084/10000000 Games Elo: -20.32 +- 0.20 (95%) [N=10000000] Games: 9911084 W: 3768907 L: 4347848 D: 1794329

1 2 3 1336 1337 1338