MattBench MattBench Workload n9x.co

Configuration

AuthorDan
Variantstandard
Creation1778620801
Dev Sourcehttps://github.com/kelseyde/hobbes-chess-engine
Dev SHA93a70f4dc9ef798919def9c3cc9e85aeb2ab7ed8
Dev Branchfeature/inference-refactor
Dev Bench1720079
Dev Avg NPS—
Dev Network
Dev OptionsThreads=1 Hash=8
Dev Time3.0+0.03
Base Sourcehttps://github.com/kelseyde/hobbes-chess-engine
Base SHAe8b03a854a71a8f04180d6dee831f78c356e6979
Base Branchmain
Base Bench1720079
Base Avg NPS—
Base Network
Base OptionsThreads=1 Hash=8
Base Time3.0+0.03
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/inference-refact... vs main

Name  | feature/inference-refactor
Elo | -2.61 +- 2.36 (95%)
SPRT | 3.0+0.03s Threads=1 Hash=8MB
LLR | -2.30 (-2.25, 2.89) [-4.00, 0.00]
Games | N: 24982 W: 5994 L: 6182 D: 12806
Penta | [225, 2937, 6345, 2769, 215]

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