FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura

factorized_lmp_tuned vs dev diff

ELO    -0.66 +- 1.84 (95%)
SPRT   40.0+0.40s Threads=1 Hash=64MB
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 31688 W: 7427 L: 7487 D: 16774
PENTA  [17, 3616, 8635, 3562, 14]
LLR History
+3.32
0.00
-3.32
-2.25+2.89
0
15,844
31,688 games
AuthorSwedishChef
Creation1774738093
Dev Sourcehttps://github.com/JonathanHallstrom/pawnocchio
Dev Sha948161aceb725def8b8941d43e592be883d4191b
Dev Branchfactorized_lmp_tuned
Dev Bench5091520
Dev Networkmixed_data_chonked5.nnue
Dev OptionsThreads=1 Hash=64 Minimal=true
Dev Time40.0+0.40
Base Sourcehttps://github.com/JonathanHallstrom/pawnocchio
Base Sha3d72e8e8fe11cc862d3784b43228e9f64540c110
Base Branchdev
Base Bench4903555
Base Networkmixed_data_chonked5.nnue
Base OptionsThreads=1 Hash=64 Minimal=true
Base Time40.0+0.40
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