Computer Chess Club Archives


Search

Terms

Messages

Subject: Testing evaluation quality with test suits

Author: Albert Bertilsson

Date: 07:25:12 12/14/03


Hi!

I've started to look at the quality of the evaluation in Sharper and have some
questions regarding a test suite I've found.

The test suite is called QuietTest and has 81660 positions, from the name and
the number of positions I guessed that this test should test the q-search
function. So I tested it with q-search only and Sharper "solves" about 13% of
the positions.

My questions are:
1. Is the test supposed to be run like I run it?
2. What does your engine score in the test?

If you don't have the test here is a sample of 100 positions, Sharper solves 11
of them, what is your score?

1B1b1k2/5ppp/pp2p3/3p4/3P4/P1N1P3/1Pb2PPP/6K1 w - - bm Kf1; id
"QuietTest.00001";
1B1b2k1/5ppp/pp2p3/3p4/3P4/P1N1P3/1Pb2PPP/6K1 b - - bm Kf8; id
"QuietTest.00002";
1B1b2k1/5ppp/pp2p3/3p4/3P4/P1NbP3/1P3PPP/6K1 w - - bm Ba7; id "QuietTest.00003";
1B1b2k1/p4ppp/1p2p3/3p4/3P4/P1NbP3/1P3PPP/6K1 b - - bm a6; id "QuietTest.00004";
1B1b4/3k1ppp/pp2p3/3p4/2bP1N2/P3P3/1P1K1PPP/8 b - - bm g5; id "QuietTest.00005";
1B1b4/3k1ppp/pp2p3/3p4/3P4/P1N1P3/1Pb1KPPP/8 w - - bm Kd2; id "QuietTest.00006";
1B1b4/3k1ppp/pp2p3/3p4/3P4/Pb2P3/1P1KNPPP/8 b - - bm Bc4; id "QuietTest.00007";
1B1b4/3k1ppp/pp2p3/3p4/3P4/PbN1P3/1P1K1PPP/8 w - - bm Ne2; id "QuietTest.00008";
1B1b4/3k3p/bp2pp2/p2p2p1/3P4/PPKNP3/5PPP/8 w - - bm Bg3; id "QuietTest.00009";
1B1b4/3k3p/pp2pp2/3p2p1/2bP4/P1KNP3/1P3PPP/8 b - - bm a5; id "QuietTest.00010";
1B1b4/4kppp/pp2p3/3p4/3P4/P1N1P3/1Pb1KPPP/8 b - - bm Kd7; id "QuietTest.00011";
1B1b4/4kppp/pp2p3/3p4/3P4/P1N1P3/1Pb2PPP/5K2 w - - bm Ke2; id "QuietTest.00012";
1B1bn3/3b2kp/3p2p1/1p1Pp3/4Pp2/2PB1P1P/6P1/2N2K2 w - - bm Ba7; id
"QuietTest.00013";
1b1q1rk1/5p1p/p5p1/3B4/4PP2/2Q5/P4P1P/5RK1 w - - bm Qf3; id "QuietTest.00014";
1b1q1rk1/5p1p/p5p1/3B4/4PP2/5Q2/P4P1P/5RK1 b - - bm Qh4; id "QuietTest.00015";
1B1Q4/5ppk/p3pn1p/P7/4P1P1/5P1P/1q4K1/8 w - - bm Kg1; id "QuietTest.00016";
1b1r1n2/5k2/R3p2p/2B3pP/4B1P1/5P2/6K1/8 w - - bm Ra8; id "QuietTest.00017";
1b1r1rk1/1p1qnp1p/p1p3p1/5p2/1P1P2b1/P3P1P1/2QN1P1P/R1R1NBK1 b - - bm g5; id
"QuietTest.00018";
1b1r1rk1/1p1qnp1p/p1p3p1/5p2/1P1P2b1/P3P3/2QN1PPP/R1R1NBK1 w - - bm g3; id
"QuietTest.00019";
1b1r1rk1/1p2qppp/p1n1p1b1/8/3Pp1B1/1QB1P1PP/PP3PN1/2RR2K1 b - - bm Rd5; id
"QuietTest.00020";
1b1r1rk1/pp2qppp/2p1pn2/8/2PP4/1Q2BBPP/PP3P2/R2R2K1 b - - bm Rd7; id
"QuietTest.00021";
1b1r1rk1/pp2qppp/2p1pn2/8/2PP4/1Q3BPP/PP3P2/R1BR2K1 w - - bm Be3; id
"QuietTest.00022";
1b1r2k1/1p1r1ppp/p5q1/3p1b2/3Q1P2/1P2P1P1/PB4BP/2R2RK1 w - - bm g4; id
"QuietTest.00023";
1b1r2k1/1p1r1ppp/p5q1/3p1b2/3Q1PP1/1P2P3/PB4BP/2R2RK1 b - - bm Bd3; id
"QuietTest.00024";
1b1r2k1/1p1r1ppp/p5q1/3p4/3Q1PP1/1P1bP3/PB4BP/2R2RK1 w - - bm Rf2; id
"QuietTest.00025";
1b1r2k1/1p2qpp1/2r1b2p/1N1p4/P2Bn3/4P2P/B3QPP1/2RR2K1 w - - bm Ba7; id
"QuietTest.00026";
1b1r2k1/1q3pp1/2p1n3/2n1p1p1/1NQ1P1P1/1P2B2P/5PB1/5R1K b - - bm Ba7; id
"QuietTest.00027";
1b1r2k1/pp1rqpp1/2p1pn1p/8/2PP4/1Q2BBPP/PP1R1P2/3R2K1 w - - bm a3; id
"QuietTest.00028";
1b1r2k1/pp1rqppp/2p1pn2/8/2PP4/1Q2BBPP/PP1R1P2/3R2K1 b - - bm h6; id
"QuietTest.00029";
1b1rr1k1/1q3pp1/2p1n3/2n1p1p1/1NQ1P1P1/1PB4P/3R1PB1/5R1K b - - bm Rxd2; id
"QuietTest.00030";
1b1rr1k1/1q3pp1/2p1n3/2n1p1p1/1NQ1P1P1/1PB4P/5PB1/3R1R1K w - - bm Rd2; id
"QuietTest.00031";
1B2kbr1/4rp1p/pq6/8/1p6/5Q2/PPP3PP/R4RK1 w - - bm Kh1; id "QuietTest.00032";
1b2n3/1P1qkpp1/8/Q3p2p/P6P/4P1P1/1R3P2/6K1 b - - bm Qc6; id "QuietTest.00033";
1b2n3/1P2kpp1/2q5/Q3p2p/P6P/4P1P1/1R3P2/6K1 w - - bm Qb4+; id "QuietTest.00034";
1B2n3/3b2kp/3p2p1/1p1Pp3/4Pp1b/2PB1P1P/4N1P1/5K2 w - - bm Nc1; id
"QuietTest.00035";
1b2r1k1/1b1n2np/pq2p1p1/1p1p4/1B1P4/1Q3N2/PP2NPPP/1B2R1K1 w - - bm Bd2; id
"QuietTest.00036";
1b2r1k1/1b1n2np/pq2p1p1/1p1p4/3P4/1Q3N2/PP1BNPPP/1B2R1K1 b - - bm Rf8; id
"QuietTest.00037";
1b2r1k1/1bq3np/p3pnp1/1pBp2N1/3P1P2/1Q6/PP2N1PP/1B2R1K1 b - - bm Nf5; id
"QuietTest.00038";
1b2r1k1/1bq3np/p3pnp1/1pBp2N1/3P4/1Q6/PP2NPPP/1B2R1K1 w - - bm f4; id
"QuietTest.00039";
1b2r1k1/1bq4p/p3pnp1/1pBp1nN1/3P1P2/1Q6/PP2N1PP/1B2R1K1 w - - bm Qh3; id
"QuietTest.00040";
1b2r1k1/1bq4p/p3pnp1/1pBp1nN1/3P1P2/7Q/PP2N1PP/1B2R1K1 b - - bm Bc8; id
"QuietTest.00041";
1b2r1k1/1q3pp1/2p1n3/2n1p1p1/1NQ1P1P1/1P5P/3B1PB1/5R1K b - - bm Rd8; id
"QuietTest.00042";
1b2r1k1/4r2p/2p2p2/1p1p1Bp1/p2P4/P1P5/1P1BbPPP/R3R2K b - - bm Kg7; id
"QuietTest.00043";
1b2r1k1/4r2p/2p2p2/1p1p2p1/p2P4/P1PB4/1P1BbPPP/R3R2K w - - bm Bf5; id
"QuietTest.00044";
1b2r1k1/r6p/2p2p2/1p1p2p1/p2P2b1/P1PB4/1P1B1PPP/R4R1K b - - bm Be2; id
"QuietTest.00045";
1b2r1k1/r6p/2p2p2/1p1p2p1/p2P2b1/P1PB4/1P3PPP/R1B2R1K w - - bm Bd2; id
"QuietTest.00046";
1b2r1k1/r6p/2p2p2/1p1p2p1/p2P4/P1PB4/1P1BbPPP/R4R1K w - - bm Rfe1; id
"QuietTest.00047";
1b2r3/1p1b1k2/1Pp3pp/2Pp1p2/3NnP1q/rN1BPR1P/2Q3P1/6RK w - - bm Bxe4; id
"QuietTest.00048";
1b2r3/1p1bqk2/1Pp3pp/2Pp1p2/3NnP2/rN1BPR1P/2Q3P1/2R4K w - - bm Rg1; id
"QuietTest.00049";
1b2r3/1p1bqk2/1Pp3pp/2Pp1p2/3NnP2/rN1BPR1P/2Q3P1/6RK b - - bm Qh4; id
"QuietTest.00050";
1b2r3/1p1bqk2/1Pp3pp/2Pp1p2/r2NnP2/1N1BPR1P/1Q4P1/2R4K w - - bm Qc2; id
"QuietTest.00051";
1b2r3/1p1bqk2/1Pp3pp/2Pp1p2/r2NnP2/1N1BPR1P/2Q3P1/2R4K b - - bm Ra3; id
"QuietTest.00052";
1b2r3/4r1k1/2p2p2/1p1p1Bpp/p2P4/P1P5/1P1BbPPP/R3R1K1 w - - bm g3; id
"QuietTest.00053";
1b2r3/4r1kp/2p2p2/1p1p1Bp1/p2P4/P1P5/1P1BbPPP/R3R1K1 b - - bm h5; id
"QuietTest.00054";
1b2r3/4r1kp/2p2p2/1p1p1Bp1/p2P4/P1P5/1P1BbPPP/R3R2K w - - bm Kg1; id
"QuietTest.00055";
1B3bk1/4p2p/p4pp1/P2b4/3P4/4PN1P/2r2PP1/R5K1 b - - bm e6; id "QuietTest.00056";
1B3bk1/7p/p3ppp1/P2b4/3P4/4PN1P/2r2PP1/1R4K1 b - - bm Rc4; id "QuietTest.00057";
1b3k1r/p3pp1p/6p1/1B1P4/4P3/5P2/P4P1P/4K2R w K - bm O-O; id "QuietTest.00058";
1b3k1r/p3pp1p/6p1/1B1P4/4P3/5P2/P4P1P/5RK1 b - - bm Bf4; id "QuietTest.00059";
1b3n2/3r1k2/R3p2p/2B3pP/4B1P1/5P2/6K1/8 b - - bm Rd8; id "QuietTest.00060";
1b3r1k/5ppp/pq6/1p1R4/1P6/P4N1P/3Q1PP1/6K1 w - - bm Ne5; id "QuietTest.00061";
1b3rk1/1b1n2np/pq2p1p1/1p1p2N1/3P4/1Q6/PP1BNPPP/1B2R1K1 b - - bm Nf6; id
"QuietTest.00062";
1b3rk1/1b4np/pq2pnp1/1p1p2N1/1B1P4/1Q6/PP2NPPP/1B2R1K1 b - - bm Re8; id
"QuietTest.00063";
1b3rk1/1b4np/pq2pnp1/1p1p2N1/3P4/1Q6/PP1BNPPP/1B2R1K1 w - - bm Bb4; id
"QuietTest.00064";
1b3rk1/1p1q2pp/p1n1p3/3r1p2/3Pp3/4P1PP/PP1RQPN1/2R1B1K1 b - - bm Nb4; id
"QuietTest.00065";
1b3rk1/1p1q2pp/p1n1p3/3r1p2/3Pp3/4P1PP/PP2QPN1/2RRB1K1 w - - bm Rd2; id
"QuietTest.00066";
1b3rk1/1p1q2pp/p3p3/3r1p2/1n1Pp3/4P1PP/PP1RQPN1/2R1B1K1 w - - bm a3; id
"QuietTest.00067";
1b3rk1/1p2q1pp/p1n1p3/3r1p2/3Pp3/2B1P1PP/PP2QPN1/2RR2K1 w - - bm Be1; id
"QuietTest.00068";
1b3rk1/1p2q1pp/p1n1p3/3r1p2/3Pp3/4P1PP/PP2QPN1/2RRB1K1 b - - bm Qd7; id
"QuietTest.00069";
1b3rk1/1p2qppp/p1n1p1b1/3r4/3Pp1B1/1QB1P1PP/PP3PN1/2RR2K1 w - - bm Be2; id
"QuietTest.00070";
1b3rk1/1p2qppp/p1n1p1b1/3r4/3Pp3/1QB1P1PP/PP2BPN1/2RR2K1 b - - bm Bh5; id
"QuietTest.00071";
1b3rk1/1p2qppp/p1n1p3/3r3b/3Pp3/1QB1P1PP/PP2BPN1/2RR2K1 w - - bm Qc2; id
"QuietTest.00072";
1b3rk1/1p2qppp/p1n1p3/3r4/3Pp3/2B1P1PP/PP2QPN1/2RR2K1 b - - bm f5; id
"QuietTest.00073";
1b3rk1/pp1rqppp/2p1pn2/8/2PP4/1Q2BBPP/PP1R1P2/R5K1 b - - bm Rfd8; id
"QuietTest.00074";
1b3rk1/pp1rqppp/2p1pn2/8/2PP4/1Q2BBPP/PP3P2/R2R2K1 w - - bm Rd2; id
"QuietTest.00075";
1b4k1/1b1q3p/p4pp1/3pn3/1B1N3P/1P2PPP1/3Q1K2/5B2 b - - bm Nc6; id
"QuietTest.00076";
1b4k1/1b5p/p4pp1/3p4/7P/1PB1PPP1/5K2/5B2 b - - bm f5; id "QuietTest.00077";
1b4k1/1b5p/p5p1/3p1p2/7P/1PBBPPP1/5K2/8 b - - bm Bc8; id "QuietTest.00078";
1B4k1/1p3pp1/6p1/1P1n4/8/b6P/4BPP1/6K1 b - - bm Bc5; id "QuietTest.00079";
1B4k1/1p3pp1/6p1/1Pbn4/8/7P/4BPP1/6K1 w - - bm Be5; id "QuietTest.00080";
1B4k1/1p3pp1/6p1/3n4/1P6/b6P/4BPP1/6K1 w - - bm b5; id "QuietTest.00081";
1B4k1/4p1bp/p4pp1/3b4/P2P4/4PN1P/2r2PP1/R5K1 b - - bm Bf8; id "QuietTest.00082";
1b4k1/5pp1/Pp6/1Bn5/2PB3p/1p3P2/4r1P1/R6K w - - bm Rb1; id "QuietTest.00083";
1B4k1/5pp1/pQ2p2p/P6n/2q1P3/5PPP/8/6K1 b - - bm Qc3; id "QuietTest.00084";
1B4k1/p3p1bp/5pp1/3b4/P2P4/4PN2/2r2PPP/R5K1 b - - bm a6; id "QuietTest.00085";
1b6/1p1b1k2/1Pp3pp/2Pp1p2/3NrP1q/rN2PR1P/1Q4P1/6RK b - - bm Ra4; id
"QuietTest.00086";
1b6/1p1b1k2/1Pp3pp/2Pp1p2/r2NrP1q/1N2PR1P/1Q4P1/R6K b - - bm Rb4; id
"QuietTest.00087";
1b6/1P2kpp1/2qn4/P3p2p/1Q5P/4P1P1/1R3P2/6K1 b - - bm Ke6; id "QuietTest.00088";
1b6/1P3pp1/2qnk3/P3p2p/1Q5P/4P1P1/1R3P2/6K1 w - - bm Qb3+; id "QuietTest.00089";
1B6/3k2p1/p1p2b1p/4p2R/P1R5/2P3P1/r4PKP/r7 w - - bm Re4; id "QuietTest.00090";
1b6/4n3/1pn1p1kp/p2p1pp1/P2P1PP1/1P1NPBBP/5K2/8 w - - bm Kg2; id
"QuietTest.00091";
1b6/4n3/1pn1pk1p/p2p1pp1/P2P1PP1/1P1NPBBP/4K3/8 w - - bm Kf2; id
"QuietTest.00092";
1b6/4n3/1pn1pk1p/p2p1pp1/P2P1PP1/1P1NPBBP/5K2/8 b - - bm Kg6; id
"QuietTest.00093";
1b6/8/5k2/pb1p2p1/3P2P1/1P1N1N2/3K4/8 w - - bm Ke3; id "QuietTest.00094";
1Bb1kb1r/5ppp/p1p1pn2/2q5/8/2N3P1/PPP2PBP/R2Q2K1 b k - bm Be7; id
"QuietTest.00095";
1bb1r1k1/1p3ppp/r1q5/1N1p4/P1nBn1BN/4P1PP/5PK1/R3Q2R b - - bm f5; id
"QuietTest.00096";
1bb1r1k1/1p3ppp/r1q5/1N1p4/P1nBn2N/4P1PP/4BPK1/R3Q2R w - - bm Bg4; id
"QuietTest.00097";
1bb1r1k1/2q4p/p3pnp1/1pBp1nN1/3P1P2/7Q/PP2N1PP/1B2R1K1 w - - bm g4; id
"QuietTest.00098";
1bb1r1k1/6qp/p2npnp1/1pBp2N1/3P1PP1/7Q/PP2N2P/1BR3K1 w - - bm Nf3; id
"QuietTest.00099";
1bb1r1k1/6qp/p2npnp1/1pBp4/3P1PP1/5N1Q/PP2N2P/1BR3K1 b - - bm Nde4; id
"QuietTest.00100";

/Regards Albert



This page took 0 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.