NCM plays each Stockfish dev build 20,000 times against Stockfish 15. 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 | 0fbad56c50edab533e5a2f0319016d14e6a9f99c |
|---|---|
| Author | pb00067 |
| Date | 2024-01-17 17:51:03 UTC |
|
Refactor code for correcting unadjustedStaticEval
Passed non-regression STC:
https://tests.stockfishchess.org/tests/live_elo/65a4df6a79aa8af82b970ca0
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 43328 W: 11103 L: 10892 D: 21333
Ptnml(0-2): 120, 4920, 11407, 5063, 154
https://github.com/official-stockfish/Stockfish/pull/4992
No functional change
|
|