MattBench MattBench Workload n9x.co

Configuration

AuthorLiamt
Variantstandard
Creation1753645589
Dev Sourcehttps://github.com/liamt19/AwesomeOpossum
Dev SHA02e7d82470127b0ccfe49e888038598369eed535
Dev Branchpolicy_128_quant
Dev Bench11923115
Dev Avg NPS—
Dev Network
Dev OptionsThreads=1 Hash=32 Minimal=true
Dev TimeN=100000
Base Sourcehttps://github.com/liamt19/AwesomeOpossum
Base SHA26c726aa263608d8d941ecc57ea9cca5d87c462d
Base Branchmain
Base Bench11705997
Base Avg NPS—
Base Network
Base OptionsThreads=1 Hash=32 Minimal=true
Base TimeN=100000
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=40
ScalingBASE 2000000 NPS

policy_128_quant vs main

Name  | policy_128_quant
Elo | -2.56 +- 4.94 (95%)
SPRT | N=100000 Threads=1 Hash=32MB
LLR | -1.31 (-2.25, 2.89) [0.00, 3.00]
Games | N: 10714 W: 4025 L: 4104 D: 2585
Penta | [533, 945, 2455, 916, 508]

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
1753945798 #554 Tecci [AwesomeOpossum] policy_128_quant build failed Full log
1753840483 #549 Tecci [AwesomeOpossum] policy_128_quant build failed Full log
1753828744 #542 Bobingstern [AwesomeOpossum] policy_128_quant build failed Full log