MattBench MattBench Workload n9x.co

Configuration

AuthorDan
Variantstandard
Creation1784068076
Dev Sourcehttps://github.com/kelseyde/hobbes-chess-engine
Dev SHAda289b52a9d86dec9e89bd1e924a1f38b992a9fb
Dev Branchfeature/finetune-wdl
Dev Bench1931756
Dev Avg NPS—
Dev Network
Dev OptionsThreads=1 Hash=64
Dev Time40.0+0.40
Base Sourcehttps://github.com/kelseyde/hobbes-chess-engine
Base SHA8293fcf57b17c9264968bf40093d7632b920a289
Base Branchmain
Base Bench1669203
Base Avg NPS—
Base Network
Base OptionsThreads=1 Hash=64
Base Time40.0+0.40
Opening BookUHO_Lichess_4852_v1.epd
Upload PGNsFALSE
Syzygy WDLDISABLED
Syzygy ADJ.OPTIONAL
Win ADJ.movecount=6 score=400
Draw ADJ.movenumber=50 movecount=8 score=25
ScalingBASE 900000 NPS

feature/finetune-wdl vs main

Name  | feature/finetune-wdl
Elo | 8.86 +- 4.57 (95%)
SPRT | 40.0+0.40s Threads=1 Hash=64MB
LLR | 2.90 (-2.25, 2.89) [0.00, 4.00]
Games | N: 5608 W: 1426 L: 1283 D: 2899
Penta | [10, 601, 1437, 748, 8]

LLR history

Hover or touch to inspect samples. Use the left and right arrow keys to move between samples, Home and End to jump, and Escape to dismiss.

Favour promising tests within their priority, using between half and twice the configured throughput.

# User Games Wins Draws Losses LL LD DD / WL DW WW Pairs Time Crash

Errors

TimeWorkerUserErrorLogs
No errors