FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Active : 15 Machines / 150 Threads / 121.98 MNPS
Priority 0
Quanticade DarkNeutrino
se-correction
praying is becoming mandatory part of engine dev
diff60.0+0.60
ELO    2.44 +- 3.02 (95%)
LLR    1.03 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 11110 W: 2609 L: 2531 D: 5970
PENTA  [4, 1159, 3148, 1243, 1]
Caissa Witek
corrhist-skip-endgame-eval
diff10.0+0.10
ELO    0.85 +- 1.39 (95%)
LLR    0.73 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 50828 W: 12924 L: 12799 D: 25105
PENTA  [15, 5239, 14776, 5374, 10]
Caissa Witek
qs-two-evasions
diff8.0+0.08
ELO    0.08 +- 1.26 (95%)
LLR    -1.14 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 81448 W: 19473 L: 19454 D: 42521
PENTA  [380, 9769, 20383, 9836, 356]
Integral Fury
razoring_all_node
diff10.0+0.10
ELO    0.57 +- 0.86 (95%)
LLR    -1.39 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 156858 W: 39037 L: 38778 D: 79043
PENTA  [320, 18297, 40959, 18510, 343]
Priority -1
Quanticade DarkNeutrino
master
25K node datagen.
diffN=25000
ELO    -0.11 +- 0.15 (95%)
GAMES  N: 14731164/30000000 W: 5167514 L: 5172188 D: 4391462
Illumina Mergener
no-gives-check-condition-in-se
No check extensions during singular extensions
diff8.0+0.08
ELO    0.19 +- 5.03 (95%)
LLR    -0.48 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 5428 W: 1174 L: 1171 D: 3083
PENTA  [35, 656, 1333, 651, 39]
Caissa Witek
qs-conthist-fix
QSearch: Fix uninitialized cont history pointers
diff10.0+0.10
ELO    -0.08 +- 1.87 (95%)
LLR    -0.66 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 34130 W: 8005 L: 8013 D: 18112
PENTA  [89, 4059, 8774, 4057, 86]
Finished
Caissa Witek
opponent-worsening
diff10.0+0.10
ELO    1.15 +- 0.92 (95%)
LLR    2.96 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 147154 W: 35360 L: 34875 D: 76919
PENTA  [497, 17400, 37377, 17727, 576]
Quanticade DarkNeutrino
hse-tuned
crash smp diff20.0+0.20
ELO    -0.00 +- 3.18 (95%)
LLR    -0.36 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 9688 W: 2217 L: 2217 D: 5254
PENTA  [3, 1010, 2816, 1014, 1]
Quanticade DarkNeutrino
noisy-triple
intended as nonreg, Realized its gainer bounds too late.
diff60.0+0.60
ELO    0.76 +- 1.79 (95%)
LLR    0.09 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 32338 W: 7592 L: 7521 D: 17225
PENTA  [8, 3533, 9017, 3602, 9]
Illumina Mergener
remove-redundant-check
Remove redundant move legality check from qsearch
diff8.0+0.08
ELO    -0.25 +- 1.35 (95%)
LLR    1.91 (-2.25, 2.89) [-3.00, 0.00]
GAMES  N: 74090 W: 16373 L: 16426 D: 41291
PENTA  [474, 8891, 18343, 8888, 449]
Integral Fury
[PlentyChess] main
Switch to the `Bulbasaur` network (#253)
diff40.0+0.40
ELO    -18.21 +- 3.33 (95%)
GAMES  N: 10008/10000 W: 2305 L: 2829 D: 4874
PENTA  [17, 1425, 2632, 925, 5]
Caissa Witek
eval-hist-2
diff10.0+0.10
ELO    -8.14 +- 3.38 (95%)
LLR    -2.97 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 10588 W: 2445 L: 2693 D: 5450
PENTA  [43, 1353, 2734, 1137, 27]
Integral Fury
vine_mix
diff40.0+0.40
ELO    14.94 +- 5.97 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 4.00]
GAMES  N: 3048 W: 826 L: 695 D: 1527
PENTA  [1, 288, 818, 413, 4]
Integral Fury
vine_mix
diff10.0+0.10
ELO    20.71 +- 7.21 (95%)
LLR    2.93 (-2.25, 2.89) [0.00, 4.00]
GAMES  N: 2284 W: 648 L: 512 D: 1124
PENTA  [2, 213, 584, 333, 10]
Integral Fury
vine_mix
diffN=25000
ELO    26.59 +- 8.01 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 2920 W: 947 L: 724 D: 1249
PENTA  [40, 287, 621, 434, 78]
Caissa Witek
eval-hist
diff10.0+0.10
ELO    -22.20 +- 5.48 (95%)
LLR    -2.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 4090 W: 838 L: 1099 D: 2153
PENTA  [21, 609, 1036, 368, 11]
Caissa Witek
master
Update README
frc diff10.0+0.10
ELO    28.69 +- 10.70 (95%)
GAMES  N: 1396/20000 W: 398 L: 283 D: 715
PENTA  [13, 126, 314, 223, 22]
Caissa Witek
master
Update README
diff1.0+0.01
ELO    -9.95 +- 13.63 (95%)
GAMES  N: 1118/40000 W: 315 L: 347 D: 456
PENTA  [33, 145, 223, 137, 21]
Caissa Witek
master
New neural net (eval-ml-8-152B-spsa) LTC: ELO 6.09 +- 3.21 (95%) SPRT 40.0+0.40s Threads=1 Hash=64MB LLR 2.95 (-2.94, 2.94) [0.00, 3.00] GAMES N: 10950 W: 2664 L: 2472 D: 5814 PENTA [11, 1188, 2894, 1362, 20] https://furybench.com/test/7437/ STC: ELO 5.97 +- 2.73 (95%) SPRT 8.0+0.08s Threads=1 Hash=16MB LLR 2.95 (-2.94, 2.94) [0.00, 2.00] GAMES N: 17164 W: 4182 L: 3887 D: 9095 PENTA [67, 1926, 4330, 2163, 96] https://furybench.com/test/7436/ Net was created by SPSA tuning previous net (eval-ml-8-152B-permuted) for 6769 iterations (108304 games) at 6+0.06 time control: https://furybench.com/tune/7435/ Only buckets 1-7 were tuned.
diff60.0+0.60
ELO    40.41 +- 4.85 (95%)
GAMES  N: 5000/40000 W: 1480 L: 901 D: 2619
PENTA  [5, 357, 1211, 908, 19]
Caissa Witek
master
New neural net (eval-ml-8-152B-spsa) LTC: ELO 6.09 +- 3.21 (95%) SPRT 40.0+0.40s Threads=1 Hash=64MB LLR 2.95 (-2.94, 2.94) [0.00, 3.00] GAMES N: 10950 W: 2664 L: 2472 D: 5814 PENTA [11, 1188, 2894, 1362, 20] https://furybench.com/test/7437/ STC: ELO 5.97 +- 2.73 (95%) SPRT 8.0+0.08s Threads=1 Hash=16MB LLR 2.95 (-2.94, 2.94) [0.00, 2.00] GAMES N: 17164 W: 4182 L: 3887 D: 9095 PENTA [67, 1926, 4330, 2163, 96] https://furybench.com/test/7436/ Net was created by SPSA tuning previous net (eval-ml-8-152B-permuted) for 6769 iterations (108304 games) at 6+0.06 time control: https://furybench.com/tune/7435/ Only buckets 1-7 were tuned.
diff10.0+0.10
ELO    29.15 +- 4.59 (95%)
GAMES  N: 6284/40000 W: 1814 L: 1288 D: 3182
PENTA  [25, 550, 1478, 1052, 37]
Quanticade DarkNeutrino
pv-triple
diff60.0+0.60
ELO    -2.30 +- 2.67 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 14212 W: 3237 L: 3331 D: 7644
PENTA  [1, 1588, 4024, 1490, 3]