FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Active : 17 Machines / 222 Threads / 160.76 MNPS
Priority 0
PlentyChess Yoshie2000
fix-one-singular
diff8.0+0.08
ELO    1.63 +- 4.11 (95%)
LLR    0.85 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 5550 W: 1418 L: 1392 D: 2740
PENTA  [7, 516, 1706, 536, 10]
Integral Fury
bad_noisy_fp_attempt_1bajillion
diff10.0+0.10
ELO    1.33 +- 5.31 (95%)
LLR    0.12 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 4194 W: 1056 L: 1040 D: 2098
PENTA  [14, 475, 1098, 501, 9]
PlentyChess Yoshie2000
fp-search-first-quiet-check
diff8.0+0.08
ELO    0.63 +- 3.31 (95%)
LLR    0.00 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 10464 W: 2529 L: 2510 D: 5425
PENTA  [15, 1228, 2723, 1255, 11]
Quanticade DarkNeutrino
master
25K node datagen.
diffN=25000
ELO    -0.11 +- 0.12 (95%)
GAMES  N: 22860486/30000000 W: 8021433 L: 8028955 D: 6810098
Caissa Witek
eval-ml-8-dtm-b0-v2
Endgames: Remove KBNvK endgame evaluator KBNvK was preferred more than other, more winning endgame, leading to draws in winning positions. STC, KBNvK_dtz60.epd: Results of New vs Old (6+0.06, 1t, 8MB, KBNvK_dtz60.epd): Elo: 95.95 +/- 12.31, nElo: 234.36 +/- 28.57 LOS: 100.00 %, DrawRatio: 45.42 %, PairsRatio: 37.75 Games: 568, Wins: 164, Losses: 11, Draws: 393, Points: 360.5 (63.47 %) Ptnml(0-2): [0, 4, 129, 145, 6], WL/DD Ratio: 0.06 LLR: 2.95 (100.0%) (-2.94, 2.94) [0.00, 5.00] STC, endgames_cdb95105.epd: ELO 11.02 +- 3.49 (95%) SPRT 10.0+0.10s Threads=1 Hash=16MB LLR 3.00 (-2.94, 2.94) [0.00, 2.00] GAMES N: 7758 W: 1948 L: 1702 D: 4108 PENTA [2, 667, 2293, 917, 0] https://furybench.com/test/7502/
diff10.0+0.10
ELO    0.43 +- 0.73 (95%)
LLR    -0.20 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 182010 W: 43580 L: 43356 D: 95074
PENTA  [34, 18891, 52932, 19113, 35]
PlentyChess Yoshie2000
rfp-cn-margin
diff8.0+0.08
ELO    -1.66 +- 3.03 (95%)
LLR    -1.20 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 12746 W: 3016 L: 3077 D: 6653
PENTA  [26, 1547, 3279, 1504, 17]
Integral Fury
fix_asp_fail_high_red
diff10.0+0.10
ELO    -5.22 +- 4.59 (95%)
LLR    -1.61 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 4792 W: 1155 L: 1227 D: 2410
PENTA  [5, 533, 1397, 451, 10]
Priority -1
Caissa Witek
pairwise-rounding
Neural net: Use rounding to nearest in pairwise multiplication
diff10.0+0.10
ELO    0.47 +- 0.69 (95%)
LLR    -0.38 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 259070 W: 61746 L: 61393 D: 135931
PENTA  [963, 30900, 65436, 31293, 943]
Caissa Witek
qs-conthist-fix
QSearch: Fix uninitialized cont history pointers
diff10.0+0.10
ELO    -0.30 +- 1.82 (95%)
LLR    -0.95 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 36178 W: 8486 L: 8517 D: 19175
PENTA  [96, 4322, 9283, 4293, 95]
Finished
PlentyChess Yoshie2000
lmp-search-first-quiet-check
diff8.0+0.08
ELO    -1.15 +- 1.93 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 30576 W: 7309 L: 7410 D: 15857
PENTA  [39, 3650, 8011, 3549, 39]
Quanticade DarkNeutrino
[Obsidian] main
search.c: Add correction margin to SE (#438)
diff10.0+0.10
ELO    -9.83 +- 5.15 (95%)
GAMES  N: 5020/5000 W: 1191 L: 1333 D: 2496
PENTA  [24, 699, 1203, 563, 21]
PlentyChess Yoshie2000
lmr-impcap-stale-2
diff40.0+0.40
ELO    -1.35 +- 2.67 (95%)
LLR    -1.24 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 14720 W: 3498 L: 3555 D: 7667
PENTA  [3, 1679, 4052, 1624, 2]
PlentyChess Yoshie2000
se-cor
diff8.0+0.08
ELO    -6.88 +- 3.98 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 7424 W: 1708 L: 1855 D: 3861
PENTA  [17, 954, 1911, 819, 11]
Integral Fury
corrhist_bad_cap_again
diff10.0+0.10
ELO    0.05 +- 1.32 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 65642 W: 16234 L: 16225 D: 33183
PENTA  [93, 7736, 17173, 7707, 112]
PlentyChess Yoshie2000
lmr-impcap-stale
diff8.0+0.08
ELO    0.19 +- 1.25 (95%)
LLR    -1.31 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 72964 W: 17680 L: 17640 D: 37644
PENTA  [103, 8603, 19024, 8655, 97]
PlentyChess Yoshie2000
lmr-impcap-stale-3
diff8.0+0.08
ELO    -1.84 +- 2.29 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 22118 W: 5309 L: 5426 D: 11383
PENTA  [31, 2692, 5730, 2575, 31]
Quanticade DarkNeutrino
master
same as before but LTC
diff60.0+0.60
ELO    30.93 +- 7.81 (95%)
GAMES  N: 1802/3000 W: 503 L: 343 D: 956
PENTA  [0, 140, 464, 294, 3]
Integral Fury
bad_noisy_fp_attempt_1bajillion
diff10.0+0.10
ELO    -3.57 +- 3.29 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 10500 W: 2502 L: 2610 D: 5388
PENTA  [22, 1263, 2781, 1169, 15]
Quanticade DarkNeutrino
master
Master against last dev prerelease to see whats up
diff10.0+0.10
ELO    32.77 +- 9.60 (95%)
GAMES  N: 1244/10000 W: 357 L: 240 D: 647
PENTA  [2, 91, 322, 202, 5]
Integral Fury
decouple_ttpv_lmr
diff10.0+0.10
ELO    -0.07 +- 1.65 (95%)
LLR    -1.72 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 42516 W: 10427 L: 10435 D: 21654
PENTA  [75, 5036, 11042, 5032, 73]
PlentyChess Yoshie2000
lmr-impcap-stale-2
diff8.0+0.08
ELO    -2.54 +- 2.57 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 17246 W: 4098 L: 4224 D: 8924
PENTA  [31, 2059, 4573, 1925, 35]
Integral Fury
double_razoring
diff10.0+0.10
ELO    -0.53 +- 1.80 (95%)
LLR    -2.28 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 35860 W: 8748 L: 8803 D: 18309
PENTA  [70, 4258, 9328, 4205, 69]
PlentyChess Yoshie2000
lmr-impcap-research-2
diff8.0+0.08
ELO    -0.97 +- 2.72 (95%)
LLR    -1.04 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 15808 W: 3823 L: 3867 D: 8118
PENTA  [21, 1932, 4040, 1892, 19]
PlentyChess Yoshie2000
lmr-impcap-research-1
diff8.0+0.08
ELO    0.24 +- 2.93 (95%)
LLR    -0.21 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 13266 W: 3242 L: 3233 D: 6791
PENTA  [14, 1562, 3479, 1557, 21]