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 | 2d3ef434b4009fcc9e198b508f00957c2d05eb1e |
---|---|
Author | Shawn Xu |
Date | 2024-07-09 16:26:35 UTC |
Tweak LMR at Root
Passed STC:
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 328192 W: 84751 L: 84014 D: 159427
Ptnml(0-2): 758, 38802, 84253, 39511, 772
https://tests.stockfishchess.org/tests/view/6689203959cb3228a4759a49
Passed LTC:
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 56748 W: 14494 L: 14136 D: 28118
Ptnml(0-2): 19, 6089, 15803, 6441, 22
https://tests.stockfishchess.org/tests/view/66892d76e59d990b103f6626
closes https://github.com/official-stockfish/Stockfish/pull/5452
Bench 1253593
|