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 |
---|---|---|---|---|---|---|---|
ncm-dbt-01 | 01:41:13 | 584652 | 1000 | 392 131 477 | +92.83 ± 9.99 | 1 22 198 273 6 | +196.45 ± 24.2 |
ncm-dbt-02 | 01:41:51 | 586881 | 1000 | 397 125 478 | +96.94 ± 9.98 | 0 28 174 296 2 | +209.91 ± 25.9 |
ncm-dbt-03 | 01:42:20 | 588197 | 1000 | 379 143 478 | +83.57 ± 9.69 | 1 20 226 248 5 | +174.55 ± 22.44 |
ncm-dbt-04 | 01:41:39 | 570528 | 1000 | 387 126 487 | +92.83 ± 9.88 | 2 21 193 282 2 | +201.19 ± 24.54 |
ncm-dbt-05 | 01:43:07 | 590773 | 1000 | 375 153 472 | +78.44 ± 9.7 | 2 23 227 247 1 | +166.66 ± 22.45 |
5000 | 1930 678 2392 | +88.89 ± 4.41 | 6 114 1018 1346 16 | +189.37 ± 10.64 |
ID | Host | Base NPS | Games | WLD | Standard Elo | Ptnml(0-2) | Gamepair Elo | CLI | PGN | ||
---|---|---|---|---|---|---|---|---|---|---|---|
398502 | ncm-dbt-02 | 585928 | 500 | 204 63 233 | +100.7 ± 13.69 | 0 10 91 147 2 | +217.85 ± 35.89 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 3322458343 \ -pgnout ncm-dbt-20250202-1236-010.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398501 | ncm-dbt-05 | 586266 | 500 | 180 76 244 | +73.34 ± 14.15 | 1 15 114 119 1 | +153.86 ± 31.85 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 470024156 \ -pgnout ncm-dbt-20250202-1236-009.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398500 | ncm-dbt-03 | 587282 | 500 | 186 71 243 | +81.37 ± 13.66 | 1 10 113 125 1 | +172.78 ± 31.83 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 3951737732 \ -pgnout ncm-dbt-20250202-1236-008.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398499 | ncm-dbt-04 | 570869 | 500 | 196 62 242 | +95.44 ± 14.4 | 2 10 91 146 1 | +209.91 ± 35.92 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 4248311165 \ -pgnout ncm-dbt-20250202-1236-007.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398498 | ncm-dbt-01 | 580406 | 500 | 188 59 253 | +91.71 ± 14.49 | 0 15 94 138 3 | +192.71 ± 35.33 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 1100540830 \ -pgnout ncm-dbt-20250202-1236-006.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398497 | ncm-dbt-02 | 587834 | 500 | 193 62 245 | +93.2 ± 14.51 | 0 18 83 149 0 | +202.15 ± 37.5 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 376414462 \ -pgnout ncm-dbt-20250202-1236-005.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398496 | ncm-dbt-03 | 589112 | 500 | 193 72 235 | +85.78 ± 13.77 | 0 10 113 123 4 | +176.33 ± 31.78 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 3629231877 \ -pgnout ncm-dbt-20250202-1236-004.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398495 | ncm-dbt-05 | 595281 | 500 | 195 77 228 | +83.57 ± 13.25 | 1 8 113 128 0 | +179.9 ± 31.72 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 1014220614 \ -pgnout ncm-dbt-20250202-1236-003.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398494 | ncm-dbt-04 | 570188 | 500 | 191 64 245 | +90.22 ± 13.55 | 0 11 102 136 1 | +192.71 ± 33.75 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 475833211 \ -pgnout ncm-dbt-20250202-1236-002.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
398493 | ncm-dbt-01 | 588899 | 500 | 204 72 224 | +93.95 ± 13.77 | 1 7 104 135 3 | +200.24 ± 33.24 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 1629460746 \ -pgnout ncm-dbt-20250202-1236-001.pgn \ -openings \ file=UHO_4060_v2.epd \ format=epd \ order=random \ -repeat \ -resign \ movecount=3 \ score=600 \ -draw \ movenumber=34 \ movecount=8 \ score=5 \ -each \ tc=30+0.3 \ timemargin=10000 \ proto=uci \ option.Hash=128 \ option.Threads=8 \ -engine \ name=20250202-1236 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:5ef1f2b13276c11814187b4ee115454803d399e3 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
Commit ID | 5ef1f2b13276c11814187b4ee115454803d399e3 |
---|---|
Author | Daniel Monroe |
Date | 2025-02-02 12:36:58 UTC |
Refactor prior reduction
Make index of reduction consistent with rest of Stack
closes https://github.com/official-stockfish/Stockfish/pull/5832
No functional change
|