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 | 186d6a41c1303317e4af31ed1859673f6699c12b |
|---|---|
| Author | mstembera |
| Date | 2026-10-10 13:40:07 UTC |
|
One instance of reductions array
STC https://tests.stockfishchess.org/tests/view/6abc689cc109910452a9aa6d
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 144288 W: 36608 L: 36515 D: 71165
Ptnml(0-2): 189, 15260, 41141, 15377, 177
Use just one reductions array by all workers instead of separate instances.
(Now possible since we don't depend on thread count any more)
closes https://github.com/official-stockfish/Stockfish/pull/7205
No functional change
|
|