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 | 01:30:27 | 583992 | 872 | 310 163 399 | +59.13 ± 10.83 | 0 40 211 183 2 | +120.11 ± 23.4 |
ncm-dbt-02 | 01:29:37 | 584643 | 868 | 306 129 433 | +71.86 ± 10.64 | 1 27 202 202 2 | +149.48 ± 23.86 |
ncm-dbt-03 | 01:30:12 | 583218 | 878 | 299 154 425 | +57.91 ± 10.73 | 0 41 213 184 1 | +118.34 ± 23.29 |
ncm-dbt-04 | 01:30:56 | 566713 | 886 | 315 157 414 | +62.63 ± 10.64 | 1 33 219 187 3 | +127.82 ± 22.86 |
ncm-dbt-05 | 01:29:12 | 581908 | 864 | 293 158 413 | +54.74 ± 10.93 | 2 38 216 175 1 | +113.22 ± 23.07 |
4368 | 1523 761 2084 | +61.24 ± 4.81 | 4 179 1061 931 9 | +125.63 ± 10.4 |
ID | Host | Base NPS | Games | WLD | Standard Elo | Ptnml(0-2) | Gamepair Elo | CLI | PGN | ||
---|---|---|---|---|---|---|---|---|---|---|---|
422795 | ncm-dbt-05 | 579992 | 364 | 123 70 171 | +50.95 ± 17.28 | 2 15 94 70 1 | +106.28 ± 34.96 | ||||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 2044579809 \ -pgnout ncm-dbt-20230924-1804-010.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422794 | ncm-dbt-02 | 585211 | 368 | 131 59 178 | +68.87 ± 16.32 | 1 11 87 85 0 | +145.84 ± 36.42 | ||||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 3109779668 \ -pgnout ncm-dbt-20230924-1804-009.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422793 | ncm-dbt-01 | 583279 | 372 | 130 63 179 | +63.27 ± 16.16 | 0 15 89 82 0 | +131.03 ± 36.09 | ||||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 4189268187 \ -pgnout ncm-dbt-20230924-1804-008.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422792 | ncm-dbt-03 | 582068 | 378 | 127 62 189 | +60.34 ± 16.69 | 0 19 86 84 0 | +124.56 ± 36.88 | ||||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 166849379 \ -pgnout ncm-dbt-20230924-1804-007.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422791 | ncm-dbt-04 | 565548 | 386 | 131 70 185 | +55.37 ± 15.76 | 1 14 101 77 0 | +115.71 ± 33.54 | ||||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 1840078302 \ -pgnout ncm-dbt-20230924-1804-006.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422790 | ncm-dbt-05 | 583824 | 500 | 170 88 242 | +57.5 ± 14.08 | 0 23 122 105 0 | +118.33 ± 30.8 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 405101584 \ -pgnout ncm-dbt-20230924-1804-005.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422789 | ncm-dbt-02 | 584076 | 500 | 175 70 255 | +74.06 ± 14.03 | 0 16 115 117 2 | +152.18 ± 31.7 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 939670559 \ -pgnout ncm-dbt-20230924-1804-004.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422788 | ncm-dbt-03 | 584369 | 500 | 172 92 236 | +56.07 ± 14.01 | 0 22 127 100 1 | +113.68 ± 30.06 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 1854853434 \ -pgnout ncm-dbt-20230924-1804-003.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422787 | ncm-dbt-01 | 584706 | 500 | 180 100 220 | +56.07 ± 14.56 | 0 25 122 101 2 | +112.14 ± 30.83 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 3322260569 \ -pgnout ncm-dbt-20230924-1804-002.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
|||||||||||
422786 | ncm-dbt-04 | 567878 | 500 | 184 87 229 | +68.27 ± 14.4 | 0 19 118 110 3 | +137.37 ± 31.31 | ↓ | |||
cutechess-cli \ -rounds 266 \ -games 2 \ -concurrency 16 \ -srand 3976992515 \ -pgnout ncm-dbt-20230924-1804-001.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=20230924-1804 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=dev_build:22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 \ -engine \ name=sf15 \ cmd=docker \ arg=run \ arg=-i \ arg=--rm \ arg=--entrypoint=/engine \ arg=stockfish:15 |
Commit ID | 22cdb6c1ea1f5ca429333bcbe26706c8b4dd38d7 |
---|---|
Author | Joost VandeVondele |
Date | 2023-09-24 18:04:42 UTC |
Explicitly invoke shell
in some cases the permission on the script might be incorrect (zip downloads?).
Explicitly invoke the shell
closes https://github.com/official-stockfish/Stockfish/pull/4803
No functional change
|