Endgame test: NNUE vs syzygy

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Dann Corbit, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
Jouni
Posts: 2386
Joined: Wed Mar 08, 2006 7:15 pm

Endgame test: NNUE vs syzygy

Post by Jouni » Thu Jan 21, 2021 8:43 pm

Yes You read right! Just for fun and curiosity I ran Stockfish dev version with NNUE against classic version with 3 GB of syzygy tables. Result:

Code: Select all

Games Completed = 1000 of 1000 (Avg game length = 80.946 sec)
Settings = Gauntlet/64MB/30000ms+300ms/M 450cp for 5 moves, D 100 moves/EPD:endgames.epd(3000)
Time = 15736 sec elapsed, 0 sec remaining
 1.  SF NNUE                  	583.5/1000	280-113-607  	(L: m=0 t=0 i=0 a=113)	(D: r=182 i=162 f=112 s=11 a=140)	(tpm=697.7 d=32.65 nps=2696242)
 2.  SF syzy                  	416.5/1000	113-280-607  	(L: m=0 t=0 i=0 a=280)	(D: r=182 i=162 f=112 s=11 a=140)	(tpm=727.3 d=34.69 nps=2759784)
NNUE was +59 ELO.
Jouni

Pi4Chess
Posts: 237
Joined: Mon Nov 16, 2020 11:13 am
Full name: Manuel Rivera

Re: Endgame test: NNUE vs syzygy

Post by Pi4Chess » Thu Jan 21, 2021 8:52 pm

Nonsense test.

Post Reply