FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura

int_multilayer vs autovec_float_multilayer diff

ELO    -71.54 +- 6.42 (95%)
CONF   N=20000 Threads=1 Hash=16MB
GAMES  N: 5634 W: 1275 L: 2419 D: 1940
PENTA  [340, 979, 1074, 333, 91]
AuthorSwedishChef
Creation1769097041
Dev Sourcehttps://github.com/JonathanHallstrom/pawnocchio
Dev Shae805b64f9d502b3faa2cc2027df1adacac5b144a
Dev Branchint_multilayer
Dev Bench3278996
Dev Networkmixed_data_2048pw_ml_int_BROKEN.nnue
Dev OptionsThreads=1 Hash=16
Dev TimeN=20000
Base Sourcehttps://github.com/JonathanHallstrom/pawnocchio
Base Sha633fa834327d56cff765c83c1245c0e60147e213
Base Branchautovec_float_multilayer
Base Bench2457398
Base Networkmixed_data_2048pw_ml_perm.nnue
Base OptionsThreads=1 Hash=16
Base TimeN=20000
Opening BookUHO_Lichess_4852_v1.epd
Upload PGNsFALSE
Syzygy WDLDISABLED
Syzygy ADJ.OPTIONAL
Win ADJ.movecount=3 score=400
Draw ADJ.movenumber=40 movecount=8 score=10
ScalingBASE 1000000 NPS
#UserGamesPentaPairsTimeCrash