FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Finished
Quanticade DarkNeutrino
Is PGO still useless after the fix ?
diff4.0+0.04
ELO    -1.08 +- 2.79 (95%)
LLR    -1.37 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 15092 W: 3709 L: 3756 D: 7627
PENTA  [64, 1674, 4120, 1621, 67]
Integral Furydiff10.0+0.10
ELO    0.33 +- 6.57 (95%)
LLR    -0.04 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 3178 W: 800 L: 797 D: 1581
PENTA  [19, 394, 758, 401, 17]
Integral Furydiff10.0+0.10
ELO    8.23 +- 3.51 (95%)
LLR    2.96 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 9376 W: 2469 L: 2247 D: 4660
PENTA  [28, 933, 2556, 1131, 40]
Integral Furydiff4.0+0.04
ELO    2.62 +- 10.08 (95%)
LLR    0.23 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 1062 W: 280 L: 272 D: 510
PENTA  [2, 109, 303, 113, 4]
Integral Furydiff4.0+0.04
ELO    -14.36 +- 6.89 (95%)
LLR    -2.35 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 2736 W: 668 L: 781 D: 1287
PENTA  [22, 357, 720, 250, 19]
Integral Furydiff4.0+0.04
ELO    -7.06 +- 4.80 (95%)
LLR    -2.29 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 5562 W: 1342 L: 1455 D: 2765
PENTA  [38, 685, 1437, 594, 27]
Caissa Witek
Makefile: Fix net download and INCBIN build race Force HTTP/1.1 with retries (some hosts hit HTTP/2 PROTOCOL_ERROR on the GitHub CDN) and download via a temporary file, so a partial transfer is never mistaken for a complete net. Make Evaluate.o and the per-arch targets depend on the net file, since it's embedded at compile time via INCBIN and could otherwise be read while still downloading under make -j.
diff10.0+0.10
ELO    4.17 +- 10.80 (95%)
GAMES  N: 1000/1000 W: 240 L: 228 D: 532
PENTA  [2, 108, 271, 114, 5]
Clarity Vast
TB optimal move filtering at root. No elo but looks nice in tournaments :)
crash diff8.0+0.08
ELO    1.62 +- 2.40 (95%)
LLR    2.89 (-2.25, 2.89) [-3.00, 1.00]
GAMES  N: 20766 W: 4783 L: 4686 D: 11297
PENTA  [102, 2214, 5651, 2317, 99]
Illumina Mergener
Remove check extension
diff8.0+0.08
ELO    -9.32 +- 7.07 (95%)
LLR    -2.25 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 2796 W: 579 L: 654 D: 1563
PENTA  [21, 380, 666, 315, 16]
Caissa Witekdiff10.0+0.10
ELO    0.58 +- 1.60 (95%)
LLR    2.95 (-2.94, 2.94) [-3.00, 0.00]
GAMES  N: 44418 W: 10552 L: 10478 D: 23388
PENTA  [129, 4900, 12073, 4982, 125]
Caissa Witekdiff1.0+0.00
ELO    27.92 +- 7.05 (95%)
LLR    3.00 (-2.94, 2.94) [-2.00, 0.00]
GAMES  N: 4378 W: 1381 L: 1030 D: 1967
PENTA  [88, 426, 895, 607, 173]
Caissa Witek
QSearch: Depth-aware pruning thresholds Scale the quiescence futility SEE threshold by how far the node sits below the main search horizon.
diff10.0+0.10
ELO    -2.17 +- 1.88 (95%)
LLR    -3.00 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 34534 W: 8011 L: 8227 D: 18296
PENTA  [127, 4161, 8878, 4003, 98]
Quanticade DarkNeutrino
search.c: Simplify ttpv && cutnode adjustment
diff60.0+0.60
ELO    -0.45 +- 1.98 (95%)
LLR    0.03 (-2.94, 2.94) [-3.00, 1.00]
GAMES  N: 26144 W: 5952 L: 5986 D: 14206
PENTA  [4, 2891, 7319, 2851, 7]
Quanticade DarkNeutrino
If it doesnt pass like this it will not pass ever
smp diff60.0+0.60
ELO    -2.09 +- 3.75 (95%)
LLR    -1.05 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6992 W: 1650 L: 1692 D: 3650
PENTA  [2, 754, 2024, 716, 0]
Integral Furydiff40.0+0.40
ELO    -0.61 +- 2.32 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 4.00]
GAMES  N: 21234 W: 5288 L: 5325 D: 10621
PENTA  [42, 2479, 5598, 2470, 28]