Commercial Release of Ethereal 13.00 (NNUE) for AVX2 Systems

[Vinvin]

Despite the fact that is the faster engine, is scores only 14/38 points (30th), so Ethereal 12.75 + Stockfish NNUE c4c3... is better (20th) Every engine without NNUE today is obsolete out-of-the-box

39 games is not enough to draw conclusions. 300 games would be way better.

[AlexChess]

Yes I know, still updating results (Ethereal 13.00 github crashes very often on my hardware) but they are already consistents with all main rating lists. Commercial 70 Elo over Igel 3.0.5 NNUE, standard github something weaker than it, and 200-300 ELO weaker than top list engines.

http://www.cegt.net/40_40%20Rating%20Li ... liste.html
https://www.sp-cc.de/index.htm
https://ccrl.chessdom.com/ccrl/404FRC/r ... _pure.html

[Nordlandia]

Can someone conduct a test of Ethereal 13 NNUE against SF Classical. The last Classical version before NNUE was added into code.

Set Classical contempt at zero.

Some suggest they're probably even in strength if not close.

https://abrok.eu/stockfish/?page=14

Bench: 4746616

[AlexChess]

Can someone conduct a test of Ethereal 13 NNUE against SF Classical. The last Classical version before NNUE was added into code.

Set Classical contempt at zero.

Some suggest they're probably even in strength if not close.

https://abrok.eu/stockfish/?page=14

Bench: 4746616

I'm interested also on a test Ethereal 13.00 NNUE commercial vs Ethereal 13.00 standard (github) , it hasn't still conducted by the main rating lists...

http://www.cegt.net/40_40%20Rating%20Li ... liste.html
https://www.sp-cc.de/index.htm
https://ccrl.chessdom.com/ccrl/404FRC/r ... _pure.html


Regards, AlexChess
https://www.chess.com/forum/view/game-a ... e-fritz-17

[AlexChess]

What is the best chess engines ranking method?

TCEC https://tcec-chess.com/ (that is considered the most reliable source) runs engines at a monstrous speed (up-to 30x as Silicon M1) but the results are consistent with my very limited hardware and also, like me, they do not play thousands of games with the same engine but they test a very wide variety of engines also private and derivatives



Regards, AlexChess
https://www.chess.com/forum/view/game-a ... e-fritz-17

[Cornfed]

https://tcec-chess.com/[/b] (that is considered the most reliable source) runs engines at a monstrous speed (up-to 30x as Silicon M1) but the results are consistent with my very limited hardware....

As it should be.

[Madeleine Birchfield]

Can someone conduct a test of Ethereal 13 NNUE against SF Classical. The last Classical version before NNUE was added into code.

Set Classical contempt at zero.

Some suggest they're probably even in strength if not close.

https://abrok.eu/stockfish/?page=14

Bench: 4746616

Ethereal 13.00 NNUE is weaker than Slowchess 2.6, which is weaker than Stockfish 10.

[Cornfed]

Can someone conduct a test of Ethereal 13 NNUE against SF Classical. The last Classical version before NNUE was added into code.

Set Classical contempt at zero.

Some suggest they're probably even in strength if not close.

https://abrok.eu/stockfish/?page=14

Bench: 4746616

Ethereal 13.00 NNUE is weaker than Slowchess 2.6, which is weaker than Stockfish 10.

ie: Buyer Beware (?)

[Chessqueen]

Can someone conduct a test of Ethereal 13 NNUE against SF Classical. The last Classical version before NNUE was added into code.

Set Classical contempt at zero.

Some suggest they're probably even in strength if not close.

https://abrok.eu/stockfish/?page=14

Bench: 4746616

Ethereal 13.00 NNUE is weaker than Slowchess 2.6, which is weaker than Stockfish 10.

ie: Buyer Beware (?)

Elo is NOT everything, if that was the case people could just download Stockfisk 13

[AlexChess]

Can someone conduct a test of Ethereal 13 NNUE against SF Classical. The last Classical version before NNUE was added into code.

Set Classical contempt at zero.

Some suggest they're probably even in strength if not close.

https://abrok.eu/stockfish/?page=14

Bench: 4746616

Ethereal 13.00 NNUE is weaker than Slowchess 2.6, which is weaker than Stockfish 10.

ie: Buyer Beware (?)

Elo is NOT everything, if that was the case people could just download Stockfisk 13

According to JCER, Ethereal 13:00 (no NNUE) is a little better than SlowChess 2.6. Could someone test 13:00 NNUE against 13:00 no NNUE and 12.75 NNUE? (suggestion: Mikeb's nn-c4c3... is already very solid https://tests.stockfishchess.org/api/nn ... 60d95.nnue , and I bet that 12.75 + official SF https://tests.stockfishchess.org/api/nn ... a22c3.nnue is stronger than 13:00 commercial...

(my match with it against 13:00 standard will follow )