SPCC: Testrun of Fat Fritz 1.0 finished

Discussion of computer chess matches and engine tournaments.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
pohl4711
Posts: 1268
Joined: Sat Sep 03, 2011 5:25 am
Location: Berlin, Germany
Contact:

SPCC: Testrun of Fat Fritz 1.0 finished

Post by pohl4711 » Tue Jan 21, 2020 7:57 am

NN-longtime-testrun of Fat Fritz 1.0 finished. A complete disappointment (like the bullet testruns by me and Andreas Strangmueller (FGRL)), even though the thinking time was long and A.Silver claimed, Fat Fritz 1.0 plays good vs. Stockfish with long thinking time. No, it does not!

Thinkingtime 8'+5'' on RTX. Average game-duration: 30 minutes. And look at this:

Code: Select all

300 SALC-Armageddon games each testrun (=all draws are a win for Black)
vs Stockfish 191210 (SPCC-Elo: 3555)

1 Lc0 0.23.1 LS 12.2 (20x256)    : 3562 300 (+153,=  0,-147), 51.0 %
2 Lc0 0.23.1 t40-1705 (30x384)   : 3548 300 (+147,=  0,-153), 49.0 %
3 Lc0 0.23.1 42741 (20x256)      : 3541 300 (+144,=  0,-156), 48.0 %
4 Lc0 0.23.1 61894 (24x320)      : 3529 300 (+139,=  0,-161), 46.3 %
4 Lc0 0.23.1 J13B.2-200 (24x320) : 3529 300 (+139,=  0,-161), 46.3 %
5 Fat Fritz 1.0 (20x256)         : 3477 300 (+117,=  0,-183), 39.0 %

https://www.sp-cc.de

(Perhaps you have to clear your browsercache or reload the website)

Post Reply