Computer Chess Club Archives


Search

Terms

Messages

Subject: 50 Test Positions, 15 Engines - Results, Comparisons

Author: Christopher A. Morgan

Date: 22:08:26 12/12/02



50 Test Positions, 15 Engines - Results, Comparisons

Recently, Gian-Carlo Pascutto, I think it was, posted about 150 position
problems, together with solutions, each with an identifying number of
ECM.xxx(x). I took the first 51, discarded one, and ran time to solve tests on
15 different chess engines for each of the 50 positions in the Fritz 7 GUI Tools
–> Analysis –> Process Test Set  window.  Below are the results of the tests.
The problems in FEN, as previously posted, follow the results.

Some details: For each of the problems I confirmed the solution by letting a
couple of engines run individually in infinite analysis mode for 5-10 minutes.
The one problem discarded had three different solutions by four different
engines.  For four of the problems, numbers 14, 28, 29 and 38 I listed the text
move as the solution together with a variation.  In one case Nimzo 8 was only
engine of four I tested with that came up with the text solution.  The other
three engines agreed on a different solution which became the variation.  For
the other three positions, multiple engines agreed on a different solution which
became the variation.

My goal was to have the majority of the engines solve every problem, so it would
be a test of how quickly a particular engine solved a problem compared to all
other engines in average speed of finding solutions to all problems, rather than
running for ten minutes (maximum allowed time per position) and not finding a
solution.

Hardware: Athlon 750, 384MB RAM, 144MB RAM hashtables, except for Chess Tiger
14, and Gambit Tiger 2 which, apparently, only allow a maximum of a 96MB
hashtable.  The times given should only be looked at in relative terms, that is
relative to the other engines.  Faster processors will get much faster times,
but I would expect that the relative percentage differences in average speed
should remain constant among different processors running the same problems with
the given solutions.

Problems 1, 24, 31, 33, and 41 took the most time for most engines, and a few
were not able to find a solution for some of these in the maximum ten minutes
allowed.  I used the default of looking forward one additional ply after a
solution was found. Times to solve problems varied tremendously by problem, and
by engine. The fastest engine overall, Nimzo 8, was easily beaten in some
problems, for instance.  Some examples: Problem 31, Gambit Tiger 2 - 30 seconds
11 ply, Nimzo 8 - 144 seconds 12 ply, and Hiarcs 8 - 353 seconds 11 ply; Problem
41, Nimzo 8 - 22 secs. 9 ply, Ruffian 1.0.1 - 112 seconds 11 ply, and Chess
Tiger 14 - 384 seconds 14 ply.

Since Nimzo was far and away the fastest problem solver among the 15 engines,
does this mean Nimzo is the fastest problem solver among the engines tested?  I
think the mathematicians here would say that for these 50 problems Nimzo is the
fastest, but that we could not extrapolate that further without a great deal of
additional testing.  Nevertheless, I do find it interesting that Nimzo 8, #15 in
the SSDF December 5, 2002 list of 128MB K6-2 450 MHz machines (#32 overall),
kicks butt on these 50 problems, easily beating Deep Fritz, #2 on the same list
(#15 overall), and Fritz 7 which is #2 overall (F7 engine used is 7.0.0.8).  I
also found it interesting that Ruffian 1.0.1, a free UCI engine came in number 2
beating a number of commercial engines.

The ChessBase file of these 50 problems is available on request from me in .cbv
format.  Each problem has an automatically generated commentary for each of the
15 engines listing it’s time to solve the problem, and the depth in plies
required.  If you click on the previous results button in the F7 GUI it will
list in order from fastest to slowest the results listed below.  If you then
click on clip file, you can paste all results into an Excel file, and see all
750 individual results by player and problem number.  You have to expand all
column widths to see the numbers, but it is formatted properly for Excel.

Results in average time in seconds to solve all problems.  All 50 problems
solved by an engine unless otherwise indicated.

	1.  Nimzo 8 - 9.6 secs.

	2.  Ruffian 1.0.1 - 16.7 secs.

	3.  Fritz 6 - 17.9 secs.

	4.  Fritz 7 - 19.0 secs.

	5.  Deep Fritz - 21.3 secs.

	6.  Gambit Tiger 2 - 22.6 secs.

	7.  Junior 7 - 28.6 secs.

	8.  Hiarcs 8 - 28.8 secs.

	9.  Goliath Light 1.5 - 29.4 secs.

	10.  Yace 0.99.56 - 49/50 problems solved, 22.5 secs.  for solved problems,
34.1  secs.  overall

	11.  Shredder 6.02 - 49/50 problems solved, 24.9 secs.  for solved problems,
36.4  secs.  overall

	12.  Chess Tiger 14 - 49/50 problems solved, 27.2 secs. for solved problems,
38.7 secs.  overall

	13.  Gandalf 4.32g - 49/50 problems solved, 31.9 secs. for solved problems,
43.3 secs.  overall

	14.  Pharaon 2.62 - 49/50 problems solved, 52.0 secs. for solved problems, 63.0
secs.  overall

	15.  Crafty 19.01 - 46/50 problems solved, 37.1 secs. for solved problems, 82.2
secs.  overall



The Position Problems:

1> r1b1r1k1/p1p3pp/2p2n2/2bp4/5P2/3BBQPq/PPPK3P/R4N1R b - - bm Bg4; id
"ECM.946";

2> 1r5r/3b1pk1/3p1np1/p1qPp3/p1N1PbP1/2P2PN1/1PB1Q1K1/R3R3 b - - bm Nxg4;
id>"ECM.949";

3> 2k4r/1pp2ppp/p1p1bn2/4N3/1q1rP3/2N1Q3/PPP2PPP/R4RK1 w - - bm Nd5; id
"ECM.952";

4> rn3rk1/4bppp/1q2p3/p2pP3/8/1PN2B1P/P4PP1/2RQ1RK1 w - - bm Bxd5; id "ECM.961";

5>2r2bk1/4qp2/3n2p1/2R1p1Np/2p1N3/r6P/1Q3PP1/3R2K1 w - - bm Rxc8; id "ECM.973";

6>r1b1rnk1/1p3pb1/1qpp2p1/2n5/2PNP2p/1PN3PP/3R1PBK/BR1Q4 b - - bm Rxa1; id
>"ECM.977";

7>r1b2rk1/pp2b3/2pn1n1p/3pNppq/3P4/BP1N2P1/P3PPBP/R1Q2RK1 w - - bm Nxc6; id
>"ECM.978";

8> 3rkb1r/1p3p2/p1n1p3/q5pp/2PpP3/1P4P1/P1Q1BPKP/R2N3R b k - bm d3; id
"ECM.986";

9> 5rk1/1r1qbnnp/R2p2p1/1p1Pp3/1Pp1P1N1/2P1B1NP/5QP1/5R1K w - - bm Qxf7+; id
>"ECM.987";

10> 5r2/1b2k2p/3bp3/5PP1/Bn1Q3P/1N6/1Pr5/1K3R2 b - - bm Rxb2+; id "ECM.993";

11> r4rk1/1b3ppp/p2q1n2/1p2N3/3P4/1B6/P1Q2PPP/2R1R1K1 w - - bm Nxf7; id
"ECM.999";

12> 3r1rk1/1b2bppp/2q1pn2/pp4Q1/3B1P2/PBN5/1PP3PP/R2R3K b - - bm Rxd4; id
>"ECM.1004";

13> 3r4/p2nrpkp/2B1p3/2P2pP1/3R3Q/q7/6PP/6RK w - - bm g6; id "ECM.1007";

14> b1n1r1k1/2q2p1p/p4Pp1/1pBP4/4B1P1/2P1Q3/P4K1P/4R3 w - - bm Qh6 (variation
Kg2); id "ECM.1009";

15> r1bqnrk1/pp2ppb1/1np3pp/4P1N1/5P2/2NBB3/PPP3PP/R2Q1RK1 w - - bm Nh7; id
>"ECM.1011";

16> 4rrk1/1bp2ppp/p1q2b1B/1pn2B2/4N1Q1/2P4P/PP3PP1/3RR1K1 w - - bm Nxc5; id
>"ECM.1016";

17> 5r1k/pb2r1bp/1p2B1p1/n7/4qNQ1/4B3/P4PPP/2RR2K1 w - - bm Rd4; id "ECM.1018";

18> 1r3rk1/5pp1/1n2qn1p/1p1pPNb1/2pP2QP/2P5/1PB3P1/R1B1R1K1 w - - bm exf6; id
>"ECM.1020";

19> 2r1rbk1/1b3ppp/pp6/2q1pNP1/Pn1RP3/2N5/1PP2QBP/5R1K w - - bm Nh6+; id
"ECM.1025";

20> r4k2/q4npp/P2P4/2p1R3/2N5/6PP/Q5K1/8 w - - bm Re7; id "ECM.1028";

21> rr4k1/2p1ppb1/3pbnpp/q1pP4/4P3/1PNNBP1P/P1KR2P1/2Q4R b - - bm Qxc3+; id
>"ECM.1038";

22> 5rk1/p1pb2pp/2p5/3p3q/2P3n1/1Q4BN/PP1Np1KP/R3R3 b - - bm Qxh3+; id
"ECM.1041";

>23> r1k4r/ppp1b3/5Npp/4pb1Q/8/1B2B3/PqP2PPP/2RR2K1 w - - bm Qxf5+; id "ECM.1045";

>24> r1bn1rk1/pp3p1p/6p1/2bR2N1/2B2B2/q1P1P3/2Q2PPP/4K2R w K - bm Nxh7; id >"ECM.1053";

>25> 2b2r2/1p2q1k1/r3pppp/4n2P/p3N3/1B4Q1/PPP3P1/3R1R1K w - - bm Rxf6; id "ECM.1057";

26> rbbq1rk1/p3nppp/1p2p3/8/1B1pN3/P2B4/1P3PPP/2RQ1RK1 w - - bm Nf6+; id
"ECM.1065";

27> rn2qbr1/2p4k/p2p1nb1/1p1Pp2p/2P4P/2NBBPN1/PP1Q4/2KR2R1 w - - bm Nxh5; id
>"ECM.1066";

28> r1bq1rk1/pp2bp1p/2p2np1/3p2B1/3P4/2NQ2N1/PPP2PPP/4RRK1 w - - bm Rxe7
(variation f4); id >"ECM.1068";

29> 2k3r1/pp2rp2/1np5/2Np1p2/P2P3p/1R2P1Pq/2Q2P1P/1R4K1 w - - bm Nxb7 (variation
a5); id >"ECM.1073";

30> 2rr1bk1/5p1p/pPN2np1/3Bp3/2Q1n3/1P2B1Pq/P3PP2/R2R2K1 b - - bm Rxd5; id
>"ECM.1076";

31> b3r3/q2B2k1/3Q2p1/1p5p/3pP3/5P2/1p4PP/5RK1 b - - bm d3+; id "ECM.1080";

32> 2r3k1/pp2n3/6pQ/4q3/8/2P1p1P1/P5BP/3R2K1 w - - bm Bd5+; id "ECM.1082";

33> 8/p3q1kp/1p2Pnp1/3pQ3/2pP4/1nP3N1/1B4PP/6K1 w - - bm Ba3; id "ECM.1084";

34> r2b1rk1/5qp1/2p2P2/2p3Pp/p6P/2Q5/PPP5/2KR2R1 w - - bm g6; id "ECM.1085";

35> 4r3/Q2bppkp/3p2p1/3Nn3/4P3/6PP/1qr2PB1/R3R1K1 b - - bm Ra8; id "ECM.1093";

36> 8/p5Q1/2ppq2p/3n1ppk/3B4/2P2P1P/P5P1/6K1 w - - bm g4+; id "ECM.1096";

37> 1r2k2r/3q2pp/p3pp2/P7/2P1Q3/8/1nB3PP/1R3R1K w k - bm Ba4; id "ECM.1098";

38> 3R4/1p2kp2/p1b1nN2/6p1/8/6BP/2r1qPPK/Q7 w - - bm Rd7+ (variation Rb8); id
"ECM.1100";

39> 1q6/2rk1p2/p1n1b1rN/3p2p1/8/3Q4/PP1B1PPP/2R1R1K1 w - - bm Nxf7; id
"ECM.1114";

40> 3r3k/p1Q3bp/2p3p1/8/2P1BRn1/1P4Pb/P1N1q2P/6BK b - - bm Nf2+; id "ECM.1122";

41> r1b4r/pp2ppk1/2np1np1/3N3p/2B1P3/q3BP2/P1PQ2PP/1R3RK1 w - - bm Nxe7; id
>"ECM.1125";

42> 5rk1/Q2nqppp/5n2/2p5/8/1B2PP1P/Pr1B1P2/R3K2R b KQ - bm Ne4; id "ECM.1127";

43> r2r1bk1/3qp2p/3pp1p1/p2n2N1/2N3Q1/BP4P1/P4PP1/2R3K1 w - - bm Nb6; id
"ECM.1131";

44> 1r3rk1/p4pbp/q1p2pp1/3p1b2/1n1P1P1B/PB3N2/1PPQR1PP/2KR4 b - - bm Bxc2; id
>"ECM.1132";

45> 1rbr2k1/4qp2/p1n2bpp/1pp1p1N1/4P3/2P1BQ1P/PPB2PP1/3RR1K1 w - - bm Bxc5; id
>"ECM.1133";

NOT USED - Engines don’t agree on best move:
>2r2rk1/1p1q1ppp/1p3n2/3p1N2/4n3/1N3Q2/PPP2PPP/R2R2K1 w - - bm Rxd5; id
>"ECM.1134";

46> 2r1r1k1/pp3pp1/3p3B/P2P1P2/2nb4/7R/1q3PQP/1B3R1K w - - bm Rb3; id
"ECM.1147";

47> 1k1r2r1/pp3p1p/B2q1n2/8/3Pb1p1/2Q5/PR3PPP/2B1R1K1 w - - bm Bf4; id
"ECM.1150";

48> k3r3/pR5p/PppR1p1p/4nP2/1PP5/8/4B1rP/2K5 w - - bm Re7; id "ECM.1151";

49> 1q3rk1/r5b1/pNp1bn1p/2Pp1n2/1P2p3/1N2P2P/PBQKB3/3R3R b - - bm Nxe3; id
>"ECM.1152";

50> r5k1/5p1p/bq1p2p1/r2Pp3/1p2N1P1/1P3P2/1KPQ3P/3R3R b - - bm Ra2+; id
"ECM.1160"



This page took 0.01 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.