https://forum.computerschach.de/cgi-bin/mwf/topic_show.pl?pid=155057
Code: Select all
Program Elo +/- Matches Score Av.Op. S.Pos. MST1 MST2 RIndex
1 StockfishMZ170522avx2-ME-12-PE+12 : 3592 7 2522 65.2 % 3483 95/128 3.1s 6.2s 0.73
2 Crystal251221 : 3589 7 2544 64.6 % 3485 93/128 2.8s 6.1s 0.62
3 Swordfish15.1-avx2 : 3586 7 2476 64.5 % 3483 92/128 2.9s 6.3s 0.69
4 ShashChess22-GoldDigger+Tal : 3586 7 2537 64.4 % 3483 95/128 3.3s 6.3s 0.64
5 CorChess3230422 : 3583 7 2451 64.0 % 3483 92/128 2.9s 6.3s 0.63
6 Stockfish15 : 3573 7 2354 62.4 % 3485 87/128 3.0s 6.8s 0.63
7 Stockfish140522 : 3572 7 2364 62.2 % 3486 87/128 3.4s 7.1s 0.61
8 Ceres0.97RC3-ap-mish-2000000 : 3568 7 2349 61.5 % 3486 83/128 3.1s 7.3s 0.62
9 Ceres0.97RC3-783257 : 3564 8 2234 60.5 % 3489 77/128 2.5s 7.5s 0.62
10 StockfishMZ170522avx2 : 3562 7 2340 60.9 % 3485 84/128 3.3s 7.3s 0.58
11 Lc0v0.30.0-dev-mish-2000000 : 3553 8 2180 58.9 % 3490 74/128 2.7s 7.9s 0.59
12 Lc0v0.30.0-dev-783272 : 3550 8 2160 58.4 % 3491 71/128 2.4s 8.0s 0.60
13 Dragon3byKomodoChess64-bit : 3538 8 2181 56.3 % 3494 72/128 3.8s 8.7s 0.50
14 Koivisto8.8 : 3447 9 1712 40.4 % 3514 37/128 3.6s 11.7s 0.30
15 Rebel15x2 : 3443 9 1707 39.6 % 3516 35/128 3.1s 11.7s 0.27
16 RubiChess20220223(bmi2) : 3432 9 1758 38.2 % 3515 38/128 5.8s 12.3s 0.20
17 Houdini4Prox64 : 3422 10 1691 36.0 % 3522 30/128 4.0s 12.4s 0.18
18 Stockfish1164POPCNT : 3414 9 1692 35.1 % 3520 32/128 5.6s 12.7s 0.14
19 Seer2.5.0 : 3403 10 1612 33.3 % 3524 27/128 4.6s 12.8s 0.18
20 ZappaMexicoIIx64 : 3391 10 1556 30.9 % 3530 20/128 2.2s 13.0s 0.20
21 DeepHIARCS15.0 : 3374 10 1537 29.0 % 3529 19/128 4.1s 13.4s 0.16
22 rofChade3.0BMI2AVX2 : 3371 9 1555 29.0 % 3527 21/128 5.3s 13.4s 0.13
23 Fritz15 : 3367 10 1534 28.1 % 3531 18/128 4.8s 13.6s 0.15
24 Fritz17Popcnt : 3356 10 1516 26.6 % 3532 15/128 3.8s 13.7s 0.13
25 DeepShredder13x64 : 3348 10 1522 25.8 % 3532 17/128 6.3s 13.8s 0.08
26 Wasp5.50 : 3346 10 1492 25.4 % 3533 14/128 4.3s 13.8s 0.13
MST1 : Mean solution time (solved positions only)
MST2 : Mean solution time (solved and unsolved positions)
RIndex: Score according to solution time ranking for each position
The upper half of the list is much better as for rankings then the lower one as error bars show too, more than this too little numbers of solved positions with this hardware- time make the ranking less reliable per se.
I just give the whole list to show the numbers of listed engines because it's a measurement for the number of matches which are taken into account as for rankings and ratings.
EloStatTS doesn't count solved positions primarily, it compares each one time of solution of each position solved and unsolved of each one single engine to each one of all of the others, just like it does with results of engine- engine- games with EloStat from same author.
StockfishMZ- setting marked with ME-12-PE+12 has Materialistic Evalution Strategy set to minium, Positional Evaluation Strategy to maximum (+12), which makes a big difference here: -12+12-setting leading, default setting ranked as nr.10.
So it seems this one setting is tuned much better as for this one special test, at least as for this one NNUE (tried ShashChess and BlueMarlin already one more time too in meantime with nn-3c0aa92af1da.nnue, getting significantly less numbers of solved positions with both of them compared to the one but last green SF dev- net nn-d0b74ce1e5eb.nnue, they are still listed with above).
Thanks a lot for the new engine- branch replacing SugaR AI:
Peter