To show you how strong Stockfish 19 is compared to 18, I used to lose 100% against 18, and I now lose 100% against 19, probably faster. Time to fire up En Croissant and see :)
The GUI page is a bit out of date imo, or I'm not sure how does the selection work because there are countles GUI options nowadays. Anyways some of the best options are not even mentioned like
Whenever I see another Stockfish update I dream of the day that I sit down and code my own chess bot that is good enough to beat me. I would be so happy if I manage to do that.
My understanding is that AlphaZero only really existed for a year or two; there's no objective way to compare it at the moment.
Leela Zero tried to open-source that work, but Stockfish incorporated a number of improvements from AlphaZero, including a neural network and a different search method, and consistently beats Leela Zero.
I have a book, "Game Changer", in which a chess expert calls out several instances where AlphaZero made moves surprising at the time; situations where all chess engines rated things one way and AlphaZero rated them differently. When I enter them into Stockfish now, it usually rates things more similarly to the way AlphaZero did, and often chooses the move chosen by AlphaZero.
The only real test of course would be to dig up AlphaZero and run it again; but I think based on the evidence we have, Stockfish of 2026 would probably trounce AlphaZero of 2018 with equivalent compute available.
On average, yes. Stockfish is the strongest engine and beats AZ-like implementations like Lc0 and the like. But on a game to game basis Lc0 can still win some games, depending on the starting position. It's rare that Lc0 can win both black and white starting from the same position, tho.
There are a few yt content creators that cover great engine games, if you're curious.
Unknown, it was only around for a little while however there is Lila which is based on the same ideas as AlphaZero (and also a fantastic project generally) they generally trade blows with Stockfish coming very slightly ahead.
That said Stockfish also uses an NN (NNUE) these days so the line is getting more blurry.
Technically nobody knows, because AlphaZero was never made public. In practice, we know Stockfish 19 would destroy it, because it destroys open-source reimplementations of AlphaZero.
They basically replaced the static position evaluation function with a NN approach and kept the rest of the tree search mostly intact.
I ran fishtest on an old cluster for a while. Was nice to watch the stockfish team methodically improving things. Basically, every commit has to show it can beat the main branch before it gets merged.
22 comments:
To show you how strong Stockfish 19 is compared to 18, I used to lose 100% against 18, and I now lose 100% against 19, probably faster. Time to fire up En Croissant and see :)
Would be nice if they included a few "notable" games in the release notes.
Presumably it's easy to highlight ones from benchmarks where the evaluation of Stockfish 19 is most significantly different from version 18?
The GUI page is a bit out of date imo, or I'm not sure how does the selection work because there are countles GUI options nowadays. Anyways some of the best options are not even mentioned like
Nocheto https://nocheto.sallyx.org/ (this my favorite)
ChessMD https://chessmd.org/
PyChess https://pychess.github.io/about/
If you like uncomplicated GUIs: http://mayura.com/chess/
I really like ChessX ( https://chessx.sourceforge.io/ ). Pychess was always unstable and slow for me.
Anyways. Now I can use an even better Stockfish to benchmark my own engine..
I have tried En Croissant and its personally its a nice GUI and easy to use. It allows you to download stockfish and others right from their GUI.
For when you need another decimal place of accuracy deciding what you should have moved instead of hanging your queen.
Whenever I see another Stockfish update I dream of the day that I sit down and code my own chess bot that is good enough to beat me. I would be so happy if I manage to do that.
Wouldn't be that hard in my case
Question: does Stockfish beat more generic systems like AlphaZero?
My understanding is that AlphaZero only really existed for a year or two; there's no objective way to compare it at the moment.
Leela Zero tried to open-source that work, but Stockfish incorporated a number of improvements from AlphaZero, including a neural network and a different search method, and consistently beats Leela Zero.
I have a book, "Game Changer", in which a chess expert calls out several instances where AlphaZero made moves surprising at the time; situations where all chess engines rated things one way and AlphaZero rated them differently. When I enter them into Stockfish now, it usually rates things more similarly to the way AlphaZero did, and often chooses the move chosen by AlphaZero.
The only real test of course would be to dig up AlphaZero and run it again; but I think based on the evidence we have, Stockfish of 2026 would probably trounce AlphaZero of 2018 with equivalent compute available.
I guess someone can twit Hassabis and ask him :D He certainly has access.
who is Hassabis?
Demis Hassabis [1], co-founder of DeepMind
[1] https://en.wikipedia.org/wiki/Demis_Hassabis
It's widely believed so because Stockfish finds all of the right (or better moves) in the games from the original paper.
I think so, see the tournament results: https://en.wikipedia.org/wiki/Top_Chess_Engine_Championship#...
On average, yes. Stockfish is the strongest engine and beats AZ-like implementations like Lc0 and the like. But on a game to game basis Lc0 can still win some games, depending on the starting position. It's rare that Lc0 can win both black and white starting from the same position, tho.
There are a few yt content creators that cover great engine games, if you're curious.
> like AlphaZero?
Unknown, it was only around for a little while however there is Lila which is based on the same ideas as AlphaZero (and also a fantastic project generally) they generally trade blows with Stockfish coming very slightly ahead.
That said Stockfish also uses an NN (NNUE) these days so the line is getting more blurry.
Technically nobody knows, because AlphaZero was never made public. In practice, we know Stockfish 19 would destroy it, because it destroys open-source reimplementations of AlphaZero.
yes and it has for a very long time. Stockfish took the neural net approach after AlphaZero showed it was a good idea as all modern chess engines have
They basically replaced the static position evaluation function with a NN approach and kept the rest of the tree search mostly intact.
I ran fishtest on an old cluster for a while. Was nice to watch the stockfish team methodically improving things. Basically, every commit has to show it can beat the main branch before it gets merged.
Like a red headed stepchild.