Author: Manfred Meiler
Date: 01:49:59 03/27/03
Go up one level in this thread
On March 26, 2003 at 22:27:01, Mike Siler wrote: >does anyone know (or know where I can find) the formula for estimating a >program's playing strength based on the BS-2830 test suite? There were 3 formulas for BS-2830 test suite: a) published in CSS 4/97: BS=2830-(GZ*GZ/289) b) published in CSS 2/98: BS(k)=2830-(GZ/1,5)-(GZ*GZ/484) c) published in CSS 3/98: BS(98)=2830-GZ-(GZ*GZ/900) GZ means "Gesamtzeit" = used solve time (for all 27 test positions) in minutes. The authors of BS-2830 (Hubert Bednorz and Heinz-Josef Schumacher) recommended to use still only the last formula BS(98). I could send you a sample EXCEL sheet prepared with formulas for BS-2830. Manfred PS: Heinz-Josef Schumacher (together with Michael Gurevich) created a newer test suite "WM-Test" with 100 test positions (38 in king attack, 36 positional and 26 in endgame), 20 minutes solve time per position. Results of 140 engines in this "WM-Test" (on Athon AMD 1400 MHz) are available for free download at http://www.computerschach.de/test/index.htm
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.