Author: Martin Andersen2
Date: 02:11:10 01/05/06
Go up one level in this thread
On January 04, 2006 at 06:28:01, Joseph Ciarrochi wrote:
>I wonder why fruit seems better that fritz9 here, wheras in the cegt list they
>are almost identical. Is there some critical difference in testing conditions
>that can explain the discrepency? Or, is this just a sampling error issue?
>
There's no discrepany between cegt and SSDF.
SSDF: Fruit 2.2.1 has a rating of 2852 +35 -33.
These numbers mean that Fruit's true rating is somewhere between
2819 and 2887. There's even a small but nonzero chance that the true
rating is outside this interval.
Fritz 9.0 has a rating of 2819 +32 -30 on SSDF, with the true rating
in the area 2789 - 2851.
The two intervals of Fruit and Fritz' ratings overlap, meaning that
their true rating could be the same.
cegt: Fruit 2.2 rating of 2789 +- 11
Fritz 9.0 rating of 2783 +- 12
So also on cegt their true rating could be the same.
Martin.
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.