NCM plays each Stockfish dev build 20,000 times against Stockfish 14. This yields an approximate Elo difference and establishes confidence in the strength of the dev builds.
| Host | Duration | Avg Base NPS | Games | WLD | Standard Elo | Ptnml(0-2) | Gamepair Elo |
|---|
| ID | Host | Base NPS | Games | WLD | Standard Elo | Ptnml(0-2) | Gamepair Elo | CLI | PGN |
|---|
| Commit ID | 4c991722447d27a3932448990187d9f05355ebf0 |
|---|---|
| Author | Robert Nurnberg @ elitebook |
| Date | 2026-09-13 07:30:02 UTC |
|
[CI] Increase number of go-mate test positions to 1000
Adding more positions for this CI run means failure will become less random, and allow us to spot regressions timely.
I also added a deterministic single threaded run as well.
Both runs now have a time out: each will fail after 30 minutes.
closes https://github.com/official-stockfish/Stockfish/pull/7073
No functional change
|
|