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 | 9829bceda90d025a5f5d7c04457902413e367041 |
---|---|
Author | Stefan Geschwentner |
Date | 2023-04-12 18:43:08 UTC |
Remove good killer reduction rule.
STC:
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 246544 W: 65646 L: 65657 D: 115241
Ptnml(0-2): 706, 27350, 67138, 27405, 673
https://tests.stockfishchess.org/tests/view/642e253277ff3301150e9aa2
LTC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 165136 W: 44878 L: 44809 D: 75449
Ptnml(0-2): 64, 15991, 50378, 16082, 53
https://tests.stockfishchess.org/tests/view/6430db07028b029b01acd87f
closes https://github.com/official-stockfish/Stockfish/pull/4519
Bench: 3746080
|