The "IQ" test doesn't contain middle-game tactical positions and technical endgames.
Here are positions dedicated to test so-called by me "quasi-intelligent" abilities of engines.
Don't use such tricks like: rule-50 changing, null-move disabling, backward-forward, special parameters (versions) and others.
The external tools like: MultiPV, tablebases, auto-play(ing), skipping (PV) moves and "Monte Carlo" are also not welcome here.
"WIN" means the correct solution and a full depth with a positive score.
Don't do the test in a machine way. Test and analyze each of items separately!
In my opinion: if an engine is able to do it (100/100), is "intelligent", in fact.
BTW. Click the d8 square on the chessboard to get the test in pgn.
The authors of studies selected to the "IQ" test:
by YACPDB:
Mendheim Julius - 1
Blathy Otto - 3, 12, 13
Benko Pal - 16, 75
Hasek Josef - 22, 28
Gurvich Abram - 23
Kasparyan Genrikh - 24
Neghina Mihai - 27
Grasemann Herbert - 37
Rudolph William - 46
Troitzky Aleksei - 57
Reti Richard - 58
Matous Mario - 60
Behting Carl - 62
Klyatskin Mikhail - 66
Kubbel Karl - 69
Novomesky Daniel - 73
Lazard Frederic - 74
Marwitz Jan - 79
Lamford Paul - 82
Simkhovich Froim - 86
by other sources:
Solovyov Y. - 6
Babic M. - 10
Neghina Mihai - 11, 31, 34, 35 (based on study), 81, 84, 87, 89, 92
Simkhovich Froim - 20
van Breukelen Gijs - 36
Hoch Yehuda & Aloni Hillel - 55
Troitzky Aleksei - 59
Smyslov Vasily - 67
Bondarenko F. & Kuznetsov A. - 68
Stavrietsky Aleksandr - 88
Kazantsev A. - 93
Ryabinin Nikolaj - 96
Neghina Mihai & Rusz Arpad- 97
Kamody Mario & Neghina Mihai - 98
Fekete Zoltan - 99 (part of study)
The "IQ" test - update
Moderators: hgm, Dann Corbit, Harvey Williamson
Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
The "IQ" test - update
Maybe, I can't be friendly, but let me be useful.
Re: The "IQ" test - update
I decided to remove two examples of this test. Why? At first, in both there is possibility to make solutions much longer.
[d]B7/p1p5/k2p4/p3p3/P1Nb1p2/6p1/7p/4K3 w - - {Ke1->c8}
34 - white King can starts from e.g. the a3 square.
[d]3k4/8/7p/2p1p1pP/1pPpPpP1/1P1P1P2/N7/2K5 w - - {Na2->h4}
81 - white King can starts from e.g. the h3 square.
Moreover, both the examples in fact are dedicated to be solving by auto-play(ing) rather than search(ing).
They are replaced by two Neghina's studies.
[d]B7/p1p5/k2p4/p3p3/P1Nb1p2/6p1/7p/4K3 w - - {Ke1->c8}
34 - white King can starts from e.g. the a3 square.
[d]3k4/8/7p/2p1p1pP/1pPpPpP1/1P1P1P2/N7/2K5 w - - {Na2->h4}
81 - white King can starts from e.g. the h3 square.
Moreover, both the examples in fact are dedicated to be solving by auto-play(ing) rather than search(ing).
They are replaced by two Neghina's studies.
Maybe, I can't be friendly, but let me be useful.
Re: The "IQ" test - update
One very important question was skipped by me here: max time per each item. I think that half hour (+ time to the end of depth), if an engine (machine) is able to get 4 000 000 nodes / second, is correct.lech wrote: ↑Sat Jan 02, 2021 11:26 amThe "IQ" test doesn't contain middle-game tactical positions and technical endgames.
Here are positions dedicated to test so-called by me "quasi-intelligent" abilities of engines.
Don't use such tricks like: rule-50 changing, null-move disabling, backward-forward, special parameters (versions) and others.
The external tools like: MultiPV, tablebases, auto-play(ing), skipping (PV) moves and "Monte Carlo" are also not welcome here.
"WIN" means the correct solution and a full depth with a positive score.
Don't do the test in a machine way. Test and analyze each of items separately!
In my opinion: if an engine is able to do it (100/100), is "intelligent", in fact.
Maybe, I can't be friendly, but let me be useful.
Re: The "IQ" test - update
I changed: 15, 71 are more difficult, in 4, 20, 39, 49 some obvious first moves are skipped.
Maybe, I can't be friendly, but let me be useful.