Author: José de Jesús García Ruvalcaba
Date: 08:57:27 05/18/99
Go up one level in this thread
On May 18, 1999 at 08:05:04, Baldomero Garcia, Jr. wrote: >On May 17, 1999 at 14:24:47, José de Jesús García Ruvalcaba wrote: > >>On May 17, 1999 at 13:32:57, Goette Patrick wrote: >>>What is the relevance of LCTII test to evaluate the strength of programs, when >>>we know the true ELO rating of CM6000 is at least 100 points higher ? >>> >> >> It has no relevance. Playing strenght is unrelated to scores in testsuites. >> >I think the difference in scores does have some relevance. It's just not very >good when the scores are so close. Obviously, if I have a program that scores >2600, while another one scores 2000, it'd be rather odd if the 2600 program >wasn't stronger than the 2000 program. >Baldo You are right if both programs are designed to play chess. But if the 2000 program is designed to play chess and the 2600 is designed to solve testsuites (or even worse, tuned for a particular testsuite being used), then it would not be surprising if the 2000 one plays stronger chess than the 2600 program. Chuy.
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.