OpenBench

OpenBench Testing Framework

Finished
Claude	Coda	main	diff	10.0+0.10	Tuning 73 Parameters 25002/25000 Iterations 100008/100000 Games Played
Claude	Coda	main	diff	40.0+0.40	Tuning 8 Parameters 2000/2000 Iterations 8000/8000 Games Played
Claude	Coda	bt4-v9-s4000-swa	diff	10.0+0.10	LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 12180 W: 3250 L: 3042 D: 5888 Ptnml(0-2): 51, 1384, 3018, 1580, 57
Claude	Coda	uci/score-scale	diff	10.0+0.10	LLR: 2.97 (-2.94, 2.94) [-2.00, 1.00] Games: 18760 W: 4596 L: 4445 D: 9719 Ptnml(0-2): 41, 1888, 5377, 2027, 47
Claude	Coda	search/rfp-deep-quad-ablation	diff	10.0+0.10	LLR: 0.94 (-2.94, 2.94) [-2.00, 1.00] Games: 25946 W: 6296 L: 6259 D: 13391 Ptnml(0-2): 89, 3058, 6646, 3087, 93
Claude	Coda	tune/core-25k-pairs2	diff	10.0+0.10	LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 73888 W: 18171 L: 17831 D: 37886 Ptnml(0-2): 206, 8728, 18789, 8962, 259
Claude	Coda	main	diff	10.0+0.10	Tuning 73 Parameters 25000/25000 Iterations 100000/100000 Games Played
Claude	Coda	tune/core-8k-pairs2	diff	10.0+0.10	LLR: -2.98 (-2.94, 2.94) [0.00, 3.00] Games: 26878 W: 6482 L: 6600 D: 13796 Ptnml(0-2): 86, 3289, 6793, 3199, 72
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: 3.01 (-2.94, 2.94) [-1.00, 2.00] Games: 130316 W: 32065 L: 31787 D: 66464 Ptnml(0-2): 438, 15609, 32829, 15801, 481
Claude	Coda	main	diff	10.0+0.10	Tuning 73 Parameters 8000/8000 Iterations 32000/32000 Games Played
Atlas	Coda	perf/history-prefetch	diff	10.0+0.10	LLR: -3.01 (-2.94, 2.94) [-2.00, 1.00] Games: 44270 W: 10736 L: 10939 D: 22595 Ptnml(0-2): 117, 4965, 12206, 4698, 149
Atlas	Coda	arch/no-king-threats-dual	diff	10.0+0.10	LLR: 0.53 (-2.94, 2.94) [-2.00, 1.00] Games: 31008 W: 7561 L: 7553 D: 15894 Ptnml(0-2): 85, 3276, 8779, 3274, 90
Atlas	Coda	perf/acc-row-prefetch	diff	10.0+0.10	LLR: 2.99 (-2.94, 2.94) [-2.00, 1.00] Games: 46200 W: 11421 L: 11285 D: 23494 Ptnml(0-2): 146, 4815, 13026, 4983, 130
Claude	Coda	tm/no-speedup-on-rising-eval	diff	10.0+0.00	LLR: -0.22 (-2.94, 2.94) [0.00, 3.00] Games: 79686 W: 20631 L: 20464 D: 38591 Ptnml(0-2): 466, 8962, 20840, 9089, 486
Claude	Coda	tm/no-speedup-on-rising-eval	diff	10.0+0.10	LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 33258 W: 8242 L: 8002 D: 17014 Ptnml(0-2): 93, 3573, 9069, 3789, 105
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: -2.95 (-2.94, 2.94) [-1.00, 2.00] Games: 31684 W: 7738 L: 7892 D: 16054 Ptnml(0-2): 104, 3945, 7914, 3759, 120
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: -2.96 (-2.94, 2.94) [0.00, 3.00] Games: 41268 W: 10112 L: 10198 D: 20958 Ptnml(0-2): 166, 5039, 10259, 5055, 115
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: 0.03 (-2.94, 2.94) [-2.00, 1.00] Games: 22484 W: 5563 L: 5577 D: 11344 Ptnml(0-2): 69, 2454, 6212, 2436, 71
Atlas	Coda	perf/threat-apply-prefetch	diff	10.0+0.10	LLR: 2.95 (-2.94, 2.94) [-2.00, 1.00] Games: 30302 W: 7483 L: 7337 D: 15482 Ptnml(0-2): 86, 3223, 8393, 3357, 92
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: 2.97 (-2.94, 2.94) [0.00, 3.00] Games: 56266 W: 13921 L: 13616 D: 28729 Ptnml(0-2): 199, 6661, 14093, 6996, 184
Atlas	Coda	nnue/dualnet-v0	diff	40.0+0.40	LLR: -2.96 (-2.94, 2.94) [0.00, 3.00] Games: 34008 W: 7963 L: 8060 D: 17985 Ptnml(0-2): 47, 4057, 8877, 3992, 31
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: 2.96 (-2.94, 2.94) [-2.00, 1.00] Games: 90052 W: 21988 L: 21878 D: 46186 Ptnml(0-2): 294, 10757, 22829, 10837, 309
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: -2.97 (-2.94, 2.94) [-1.00, 2.00] Games: 116680 W: 28683 L: 28774 D: 59223 Ptnml(0-2): 392, 14128, 29405, 14009, 406
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: -2.97 (-2.94, 2.94) [-1.00, 2.00] Games: 6784 W: 1600 L: 1775 D: 3409 Ptnml(0-2): 44, 870, 1714, 745, 19
Atlas	Coda	nnue/dualnet-v0	diff	10.0+0.10	LLR: -2.94 (-2.94, 2.94) [0.00, 3.00] Games: 21304 W: 5094 L: 5223 D: 10987 Ptnml(0-2): 80, 2616, 5375, 2515, 66

1 2 3 26 27 28 29 30 138 139 140