STS with pv?

[Ferdy]

Thank you Ferdy. Yesterday I ran your script sts-rating.py 3 times on STS1-STS15_LAN_v3.epd from your github. I was a bit surprised by this:

(13 gen i7-13700, 32 GB RAM) Hash: 256, Threads: 8, time/pos: 2.000s - total score 88.6 %
(13 gen i7-13700, 32 GB RAM) Hash: 256, Threads: 16, time/pos: 8.000s - total score 88.9 %
(Old laptop, Dell Latitude, core i5, 4 GB RAM) Hash: 128, Threads: 1, time/pos: 2.000s - total score 88.3 %

So not must difference in score between a powerful machine with more time per move, more threads, and a low end laptop with small value of movetime. 1 thread. STS 9, 7, 11, 12 are consistently low scoring in all 3 tests.

Is there a way I can run analysis on the epd file and create a pgn with pv or include pv in epd as a comment? What tool on linux does this?

Is that 2, 8 and 2 seconds? If so you need more time to improve the rate. Also there are positions in the original STS pos that have now a different best moves according to latest engines.

[Ferdy]

This is the latest sts pos in epd format from my google drive. This is based from the re-analyzed positions that are checked so far.

The scoring system points are proportional to the top 10 evaluations.

Sample output from this test set.

Code: Select all

                  name  top1  ttop1  top1%  points  tpoints  points%   mtms
0       Stockfish 16.1   820   1035  79.23   94964   103500    91.75  100.0
1         Stockfish 15   818   1035  79.03   95905   103500    92.66  100.0
2           Berserk 13   809   1035  78.16   94731   103500    91.53  100.0
3         Berserk 12.1   803   1035  77.58   94381   103500    91.19  100.0
4         Stockfish 14   785   1035  75.85   93319   103500    90.16  100.0
5           Seer 2.8.0   769   1035  74.30   92163   103500    89.05  100.0
6           Seer 2.7.0   755   1035  72.95   92059   103500    88.95  100.0
7   CT800 V1.44 64 bit   448   1035  43.29   69429   103500    67.08  100.0
8   CT800 V1.43 64 bit   438   1035  42.32   68085   103500    65.78  100.0
9   CT800 V1.42 64 bit   423   1035  40.87   66451   103500    64.20  100.0
10         CDrill 2000   418   1035  40.39   66347   103500    64.10  100.0
11         CDrill 1800   334   1035  32.27   57304   103500    55.37  100.0

[chesskobra]

Thanks. I also found epd-analyzer in your github, which is also very useful. Thanks for all your programs.