OpenBench Testing Framework

Finished
rounded-lmr-division
8.0+0.08
Elo: -12.67 +- 7.81 [0.00, 5.00]
Games: 2002 W: 414 L: 487 D: 1101
Ptnml(0-2): 6, 281, 496, 216, 2
rounded lmr division
do-lmr-later-in-root
N=200000
Elo: -0.00 +- 0.00 [0.00, 5.00]
Games: 316 W: 75 L: 75 D: 166
Ptnml(0-2): 0, 0, 158, 0, 0
do lmr later in root
do-lmr-later-in-root
N=10000
Elo: -0.00 +- 0.00 [0.00, 5.00]
Games: 4496 W: 1398 L: 1398 D: 1700
Ptnml(0-2): 0, 0, 2248, 0, 0
do lmr later in root
fail-firm-multicut
8.0+0.08
Elo: -0.65 +- 4.59 [0.00, 5.00]
Games: 5860 W: 1403 L: 1414 D: 3043
Ptnml(0-2): 19, 707, 1490, 694, 20
fail firm multicut
[Icarus] 6fe827a790934bb6585988293a22d29b47be81e1 *
40.0+0.40
Elo: -56.46 +- 15.42 (95%) [N=1024]
Games: 658 W: 126 L: 232 D: 300
Ptnml(0-2): 14, 127, 143, 41, 4
Update WDL model Based on ~30k games at 20+0.2s.
[Prune] 591318a3c85eb1d449b900701269391e1eeba67d
40.0+0.40
Elo: 72.11 +- 14.12 (95%) [N=1024]
Games: 606 W: 215 L: 91 D: 300
Ptnml(0-2): 0, 28, 129, 140, 6
Update WDL model Based on ~30k games at 20+0.2s.
[Icarus] 6fe827a790934bb6585988293a22d29b47be81e1
40.0+0.40
Elo: -15.80 +- 11.14 (95%) [N=1024]
Games: 1034 W: 242 L: 289 D: 503
Ptnml(0-2): 12, 131, 266, 108, 0
Update WDL model Based on ~30k games at 20+0.2s.
[Icarus] 6fe827a
20.0+0.20
Elo: -29.16 +- 10.24 (95%) [N=2048]
Games: 1290 W: 266 L: 374 D: 650
Ptnml(0-2): 12, 210, 298, 124, 1
Update WDL model Based on ~30k games at 20+0.2s.
master *
20.0+0.20
Elo: 150.14 +- 10.48 (95%) [N=2048]
Games: 2056 W: 1038 L: 201 D: 817
Ptnml(0-2): 4, 49, 281, 494, 200
Update Github Actions action versions
no-normalization
20.0+0.20
Elo: 0.14 +- 1.87 (95%) [N=30000]
Games: 30012 W: 7523 L: 7511 D: 14978
Ptnml(0-2): 37, 3227, 8465, 3241, 36
no normalization
master
8.0+0.08
Elo: 61.01 +- 6.04 (95%) [N=4096]
Games: 4096 W: 1424 L: 712 D: 1960
Ptnml(0-2): 14, 267, 834, 859, 74
Update Github Actions action versions
master
40.0+0.40
Elo: 76.38 +- 11.34 (95%) [N=1024]
Games: 1026 W: 358 L: 136 D: 532
Ptnml(0-2): 0, 51, 205, 241, 16
Update Github Actions action versions
upcoming-repetition-detection *
8.0+0.08
Elo: 0.60 +- 1.72 [0.00, 5.00]
Games: 41170 W: 9635 L: 9564 D: 21971
Ptnml(0-2): 131, 4846, 10555, 4927, 126
upcoming repetition detection
random-fen-skipping
40.0+0.40
Elo: -3.07 +- 4.27 [0.00, 5.00]
Games: 6444 W: 1476 L: 1533 D: 3435
Ptnml(0-2): 10, 807, 1644, 752, 9
net
random-fen-skipping
8.0+0.08
Elo: 0.30 +- 3.00 [0.00, 5.00]
Games: 14810 W: 3728 L: 3715 D: 7367
Ptnml(0-2): 87, 1784, 3639, 1819, 76
net
random-fen-skipping
N=40000
Elo: 4.01 +- 3.15 [0.00, 5.00]
Games: 20350 W: 6152 L: 5917 D: 8281
Ptnml(0-2): 455, 2404, 4305, 2473, 538
net
net-max-eval
8.0+0.08
Elo: 2.60 +- 3.73 [-5.00, 0.00]
Games: 9492 W: 2431 L: 2360 D: 4701
Ptnml(0-2): 32, 1168, 2295, 1199, 52
net
net-max-eval
N=40000
Elo: -0.69 +- 5.93 [-5.00, 0.00]
Games: 5522 W: 1625 L: 1636 D: 2261
Ptnml(0-2): 130, 634, 1249, 613, 135
net
net-max-eval
N=40000
Elo: -0.61 +- 4.73 [-5.00, 0.00]
Games: 9090 W: 2650 L: 2666 D: 3774
Ptnml(0-2): 223, 1112, 1884, 1110, 216
net
net-max-eval
N=25000
Elo: -18.88 +- 10.45 [0.00, 5.00]
Games: 1916 W: 534 L: 638 D: 744
Ptnml(0-2): 61, 263, 392, 203, 39
net
dual-activation
40.0+0.40
Elo: 7.21 +- 4.45 [0.00, 5.00]
Games: 5980 W: 1481 L: 1357 D: 3142
Ptnml(0-2): 11, 663, 1515, 793, 8
dual-activation
N=25000
Elo: 8.35 +- 5.36 [0.00, 5.00]
Games: 7612 W: 2398 L: 2215 D: 2999
Ptnml(0-2): 194, 874, 1538, 955, 245
dual activation
multilayer-ranger
40.0+0.40
Elo: 65.09 +- 10.55 (95%) [N=1024]
Games: 1026 W: 346 L: 156 D: 524
Ptnml(0-2): 1, 48, 229, 230, 5
ml ranger
master
40.0+0.40
Elo: 62.96 +- 10.53 (95%) [N=1024]
Games: 1032 W: 348 L: 163 D: 521
Ptnml(0-2): 1, 49, 236, 224, 6
Improve nnue_index readability * Move Bitboard::flip_vertically to Square::mirror_vertically * Add mirror_horizontally_if
master
40.0+0.40
Elo: -2.14 +- 10.43 (95%) [N=1024]
Games: 810 W: 177 L: 182 D: 451
Ptnml(0-2): 1, 76, 255, 73, 0
Improve nnue_index readability * Move Bitboard::flip_vertically to Square::mirror_vertically * Add mirror_horizontally_if