MattBench MattBench Workload n9x.co

Configuration

AuthorBobingstern
Variantstandard
Creation1754026634
Dev Sourcehttps://github.com/Bobingstern/Tarnished
Dev SHA3a3140bdd7e44514fe3f1f44de15b390042d863c
Dev Branchtt-corrected-eval
Dev Bench2164341
Dev Avg NPS—
Dev Networkdfrc-mixed
Dev OptionsThreads=1 Hash=32
Dev Time8.0+0.08
Base Sourcehttps://github.com/Bobingstern/Tarnished
Base SHA342f0d3ec47b060aa241b32aa72bc86737d362b3
Base Branchmaster
Base Bench2235684
Base Avg NPS—
Base Networkdfrc-mixed
Base OptionsThreads=1 Hash=32
Base Time8.0+0.08
Opening BookUHO_Lichess_4852_v1.epd
Upload PGNsFALSE
Syzygy WDLDISABLED
Syzygy ADJ.OPTIONAL
Win ADJ.movecount=3 score=400
Draw ADJ.movenumber=32 movecount=8 score=10
ScalingDEV 1400000 NPS

tt-corrected-eval vs master

Name  | tt-corrected-eval
Elo | 2.87 +- 2.08 (95%)
SPRT | 8.0+0.08s Threads=1 Hash=32MB
LLR | 2.97 (-2.94, 2.94) [0.00, 3.00]
Games | N: 31198 W: 7614 L: 7356 D: 16228
Penta | [175, 3677, 7655, 3899, 193]

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
1754027054 #510 dragjon [Tarnished] tt-corrected-eval build failed Full log