CCRL rating lists updated (3rd October 2008)

[Graham Banks]

The latest updates of the CCRL Rating Lists and Statistics are available for viewing at:
http://www.computerchess.org.uk/ccrl/4040/ (40/40)
http://computerchess.org.uk/ccrl/404/ (40/4)
The live link to the 40/4 list given below is currently the most up to date for that list.

The lists sometimes get updated during the week and these updates can be viewed here:
http://www.computerchess.org.uk/ccrl/4040.live/ (40/40)
http://computerchess.org.uk/ccrl/404.live/ (40/4)
However, no game downloads are available from these live links.

The links to the various rating lists can be found just beneath the default Best Versions list.
For example there is a 32-bit Single CPU list.

Our 40 moves in 40 minutes repeating and 40 moves in 4 minutes repeating are both adjusted to the AMD64 X2 4600+ (2.4GHz).

Currently active testers are:
Graham Banks, Ray Banks, Shaun Brewer, Kirill Kryukov, Dom Leste, Tom Logan, Wassim Saeed, Charles Smith, George Speight and Gabor Szots.
Currently inactive testers are:
Sarah Bird, Andreas Schwartmann, Chris Taylor, Martin Thoresen and Chuck Wilson.

Be aware that in the early stages of testing, an engine's rating can often fluctuate a lot.
It is strongly advised to also look at the many other rating lists available in order to get a more accurate overall picture of an engine's rating relative to others.


40/40 Notes


4CPU 64-bit Engines

With 700+ games now under its belt, Rybka 3 remains close to 150 elo clear at the top.
Naum 3.1 and Zappa Mexico II in second and third spots are very similar in strength to each other.
There is a 60 elo gap back to Deep Shredder 11, Deep Sjeng 3.0, Hiarcs 12 and Toga II 1.4.1SE. These four engines have an edge over Deep Fritz 10.1 which in turn has an advantage over Glaurung 2.1 and the still private Bright 0.3d.
Loop M1-T is further back.

The relative ratings of the 2CPU engines that have been well tested are pretty much the same as their 4CPU counterparts.


Single CPU Engines

Rybka 3 is close to 200 elo ahead of other engines in this category.
Naum 3.1 lies in second spot, narrowly ahead of the tightly bunched Fritz 11, Zappa Mexico II, Shredder 11, Deep Sjeng 3.0 and Toga II 1.4.1SE.
Hiarcs 12 is further back with a clear advantage over Glaurung 2.1, Fruit 2.3.1, Loop 13.6, Thinker 5.1e Passive, Cyclone 1.0 and Bright 0.3d (private).


Free Single CPU Engines

Rybka 2.2 heads the field with a 50+ elo gap back to Toga II 1.4.1SE.
There is a similar gap back to Glaurung 2.1, Fruit 2.3.1, Thinker 5.2e Passive and Cyclone 1.0. This group holds a definite edge over Spike 1.2 Turin and Bright 0.3a.

CCRL tests a wide range of amateur engines (defined as free and having never gone commercial), ranging right down to the 1900 elo level. The intention is to get well over 200 games for each of these engines. We see it is a way of supporting and hopefully motivating these engine authors with their efforts.


Blitz Notes

An enormous amount of work goes into the blitz list and with over 300,000 games in the database, it is well worth a visit.

Of special interest to some will be the best free 1CPU engines list which is being constructed through a systematic testing approach as mentioned here:
http://kirill-kryukov.com/chess/discuss ... f=7&t=3271


FRC Notes

Ray tests only those engines that can play FRC through the Shredder Classic GUI.
If engine authors have a new and stable version of their engine that will run under this GUI, they should contact Ray if they wish to see it tested.

Rybka 3 has a massive 200 elo lead over the closely grouped Shredder 11, Naum 3.1 and Deep Sjeng 3.0.
Hiarcs Paderborn 2007 in fifth spot is well ahead of Fruit 051103 and Loop 10.32f (the most recent Loop version that could play FRC).

For FRC the best list to look at is the pure list.
http://www.computerchess.org.uk/ccrl/404FRC/


Stats/Presentation Notes

The LOS (likelihood of superiority) stats to the right hand side of each rating list tell you the likelihood in percentage terms of each engine being superior to the engine directly below them.

All games are available for download by engine, by month or by ECO code.
ELO ratings are now saved in all game databases for those engines that have 200 games or more.

Clicking on an engine name will give details as to opponents played plus homepage links where applicable.

Custom lists of engines can be selected for comparison.

An openings report page lists the number of games played by ECO codes with draw percentage and White win percentage. Clicking on a column heading will sort the list by that column.

[swami]

Rybka 3 has a massive 200 elo lead over the closely grouped Shredder 11, Naum 3.1 and Deep Sjeng 3.0.
Hiarcs Paderborn 2007 in fifth spot is well ahead of Fruit 051103 and Loop 10.32f (the most recent Loop version that could play FRC).

Hiarcs now 5th?! I hope they release the new version just after this WCCC? (they usually release a new version after some major tournament)

Thanks for the detailed report, Graham.

[Graham Banks]

Rybka 3 has a massive 200 elo lead over the closely grouped Shredder 11, Naum 3.1 and Deep Sjeng 3.0.
Hiarcs Paderborn 2007 in fifth spot is well ahead of Fruit 051103 and Loop 10.32f (the most recent Loop version that could play FRC).

Hiarcs now 5th?! I hope they release the new version just after this WCCC? (they usually release a new version after some major tournament)

Thanks for the detailed report, Graham.

You're welcome Swami. Somebody has to do it.

Cheers, Graham.

[ozziejoe]

I think deep fritz 11 might be the next "challenger" to rybka. At least, d f11 should get within 50 pnts

best
J

[WinPooh]

Could you please replace GreKo 5.9 with GreKo 6.0 in the tests? GreKo 5.9 has critical bugs in move generator, and can't be considered as a legal-playing chess engine. It can lose games due to illegal moves.

[Tony Thomas]

I think deep fritz 11 might be the next "challenger" to rybka. At least, d f11 should get within 50 pnts

best
J

Provided that the only thing they add to Deep Fritz 11 is SMP capability we can expect an increase of around 105 points (Fritz 10 rating 2885, deep Fritz 10.1 2990), that would make it rated 2963+105----> 3068. That would put DF 11 rated around the same strength as Naum and Zapper.. Provided that they had all this time to improve the program, your estimate of within 50 points sounds reasonable.

[Graham Banks]

Could you please replace GreKo 5.9 with GreKo 6.0 in the tests? GreKo 5.9 has critical bugs in move generator, and can't be considered as a legal-playing chess engine. It can lose games due to illegal moves.

Hi Vladimir,

once my current tournaments have finished, I'll switch to GreKo 6.0.
You can be assured that all GreKo 5.9 games on our lists are legal games.
Thanks for your continuing efforts with GreKo. It seems to be making good progress.

Regards, Graham.

[Ovyron]

I'd consider it a big failure. Their goal now should be to beat free Rybka 2.2n2 convincingly, it's reasonable and at least they could say they're better than the top freeware software.

If it takes them years to achieve this, so be it. Hopefully Vas won't release a stronger free version by then.

[Norm Pollock]

Hi Graham,

Looking at the "killed engines" list this week, I noticed the inclusion of "Strelka" and its 1364 games. This would seem to mean that "Strelka" is no longer rated by CCRL and that its games are no longer part of the CCRL databases for rating purposes and for download.

-Norm

[Graham Banks]

Hi Graham,

Looking at the "killed engines" list this week, I noticed the inclusion of "Strelka" and its 1364 games. This would seem to mean that "Strelka" is no longer rated by CCRL and that its games are no longer part of the CCRL databases for rating purposes and for download.

-Norm

The 40/40 testers decided to remove it from the 40/40 lists.

Regards, Graham.