FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura

factorized_lmp_tuned vs dev diff

ELO    -3.14 +- 3.15 (95%)
SPRT   10.0+0.10s Threads=1 Hash=16MB
LLR    -2.30 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 12072 W: 2769 L: 2878 D: 6425
PENTA  [27, 1505, 3082, 1394, 28]
ApproveRestartDelete
LLR History
+3.32
0.00
-3.32
-2.25+2.89
0
6,036
12,072 games
AuthorSwedishChef
Creation1774736613
Dev Sourcehttps://github.com/JonathanHallstrom/pawnocchio
Dev Sha948161aceb725def8b8941d43e592be883d4191b
Dev Branchfactorized_lmp_tuned
Dev Bench5091520
Dev Networkmixed_data_chonked5.nnue
Dev OptionsThreads=1 Hash=16 Minimal=true
Dev Time10.0+0.10
Base Sourcehttps://github.com/JonathanHallstrom/pawnocchio
Base Sha3d72e8e8fe11cc862d3784b43228e9f64540c110
Base Branchdev
Base Bench4903555
Base Networkmixed_data_chonked5.nnue
Base OptionsThreads=1 Hash=16 Minimal=true
Base Time10.0+0.10
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
Copy Stat Block
Copy Stat Block (Code Blocked)
#UserGamesPentaPairsTimeCrash