Latest update: 2021/03/01: Stockfish 210226 (+5 Elo to Stockfish 13) (Ordo-calculation fixed to Stockfish 13 = 3723 Elo)
See the individual statistics of engine-results [You must be registered and logged in to see this link.]Download the current gamebase [You must be registered and logged in to see this link.] Program Elo + - Games Score Av.Op. Draws
1 Stockfish 210226 avx2 : 3728 8 8 7000 76.6 % 3500 44.9 %
2 CFish 12 3xCerebellum : 3725 8 8 7000 86.1 % 3387 27.3 %
3 Stockfish 210111 avx2 : 3724 7 7 7000 78.0 % 3479 42.5 %
4 Stockfish 13 210218 : 3723 6 6 10000 72.8 % 3526 51.0 %
5 SF Fat Fritz 2 avx2 : 3718 7 7 8000 73.7 % 3513 49.3 %
6 CFish 12 avx2 : 3702 8 8 7000 84.6 % 3387 29.1 %
7 Stockfish 12 200902 : 3683 4 4 28000 76.9 % 3446 41.4 %
8 SF Fat Fritz 2 github : 3677 7 7 7000 73.3 % 3483 48.5 %
9 KomodoDragon 1.0 avx2 : 3647 5 5 19000 69.4 % 3479 47.5 %
10 SF 200910 miniNNue avx2 : 3614 7 7 7000 72.1 % 3435 43.2 %
11 Stockfish 200731 popc : 3600 7 7 7000 80.5 % 3344 36.2 %
12 Stockfish 11 200118 : 3563 5 5 17000 69.5 % 3401 41.6 %
13 Stockfish 10 181129 : 3524 5 5 15000 78.5 % 3287 37.7 %
14 KomodoDragon 1.0 MCTS : 3479 6 6 7000 57.6 % 3425 57.1 %
15 Stockfish 9 180201 : 3474 8 8 5000 74.9 % 3272 41.7 %
16 Komodo 14.1 x64 : 3453 6 6 8000 56.3 % 3409 55.6 %
17 Komodo 14 bmi2 : 3443 4 4 19000 51.3 % 3438 51.6 %
18 Houdini 6 pext : 3439 2 2 56000 55.0 % 3404 46.9 %
19 Nemorino 6.00 avx2 : 3438 4 4 25000 46.1 % 3476 50.4 %
20 Komodo 13.3 bmi2 : 3437 6 6 8000 62.8 % 3341 49.9 %
21 Fire 8 popc : 3430 6 6 8000 39.7 % 3519 50.8 %
22 Komodo 13.1 bmi2 : 3424 5 5 11000 62.0 % 3333 48.8 %
23 Slow Chess 2.5 avx2 : 3422 5 5 15000 37.0 % 3535 46.0 %
24 Komodo 12.3 bmi2 : 3411 7 7 7000 62.7 % 3313 49.4 %
25 Nemorino 6.05 avx2 : 3406 7 7 7000 42.8 % 3467 51.0 %
26 Ethereal 12.75 avx2 : 3397 4 4 25000 40.8 % 3478 49.2 %
27 Ethereal 12.62 avx2 : 3389 6 6 8000 49.1 % 3401 54.6 %
28 Slow Chess 2.4 popc : 3373 5 5 12000 43.7 % 3426 52.3 %
29 Ethereal 12.50 popc : 3356 6 6 7000 45.8 % 3395 55.2 %
30 RubiChess 2.0 avx2 : 3355 6 6 12000 30.2 % 3526 45.5 %
31 Slow Chess 2.3 popc : 3343 4 4 14000 42.3 % 3406 52.2 %
32 Komodo 14 MCTS : 3339 7 7 5000 44.4 % 3384 53.4 %
33 Ethereal 12.25 pext : 3337 5 5 12000 35.2 % 3470 46.4 %
34 Pedone 3 avx2 : 3329 6 6 8000 33.4 % 3466 46.7 %
35 Slow Chess 2.2 popc : 3328 6 6 11000 32.9 % 3482 42.7 %
36 Igel 2.9.0 popavx2 : 3328 5 5 12000 32.5 % 3474 47.5 %
37 RubiChess 1.9dev nnue : 3319 6 6 8000 31.8 % 3470 45.6 %
38 Ethereal 12.00 pext : 3316 5 5 9000 43.1 % 3369 50.8 %
39 Ethereal 11.75 pext : 3308 6 6 9000 39.3 % 3391 53.2 %
40 Xiphos 0.6 bmi2 : 3302 3 3 31000 36.2 % 3420 48.9 %
41 Fire 7.1 popc : 3300 3 3 41000 41.9 % 3371 50.7 %
42 Xiphos 0.5.6 bmi2 : 3287 7 7 7000 41.2 % 3355 54.6 %
43 Minic 2.51 nasc_nutr : 3282 6 6 7000 31.2 % 3435 45.0 %
44 Ethereal 11.53 pext : 3280 6 6 7000 42.2 % 3341 53.4 %
45 Komodo 12.3 MCTS : 3275 7 7 7000 42.7 % 3333 46.3 %
46 Ethereal 11.25 pext : 3270 8 8 6000 38.4 % 3361 51.0 %
47 rofChade 2.3 bmi2 : 3256 6 6 11000 33.8 % 3387 47.5 %
48 Booot 6.4 popc : 3243 7 7 6000 31.1 % 3393 46.5 %
49 Schooner 2.2 popc : 3241 7 7 6000 31.3 % 3389 50.3 %
50 Laser 1.7 bmi2 : 3217 7 7 6000 30.8 % 3370 45.8 %
51 Fizbo 2 bmi2 : 3212 8 8 5000 36.0 % 3324 39.0 %
52 Fritz 17 : 3211 7 7 6000 29.4 % 3376 44.2 %
53 Shredder 13 x64 : 3209 8 8 6000 31.9 % 3358 42.6 %
54 RubiChess 1.8 popc : 3207 6 6 7000 32.0 % 3344 46.1 %
55 Defenchess 2.2 popc : 3204 8 8 5000 26.6 % 3393 41.8 %
56 Booot 6.3.1 popc : 3199 8 8 5000 34.0 % 3327 44.1 %
57 Andscacs 0.95 popc : 3167 9 9 5000 23.1 % 3390 35.4 %
The version-numbers (180622 for example) of the engines are the date of the latest patch, which was included in the Stockfish sourcecode,
not the release-date of the engine-file. Especially the asmFish-engines are often released much later!!
Below you find a diagram of the progress of Stockfish in my tests since August 2020. And below that diagram, the older diagrams. You can save the diagrams (as a JPG-picture (in originial size)) on your PC with mouseclick (right button) and then choose "save image"...The Elo-ratings of older Stockfish dev-versions in the Ordo-calculation can be a little different to the Elo-"dots" in the diagram, because the results/games of new Stockfish dev-versions - when getting part of the Ordo-calculation - can change the Elo-ratings of the opponent engines and that can change the Elo-ratings of older Stockfish dev-versions (in the Ordo-calculation / ratinglist, but not in the diagram, where all Elo-"dots" are the rating of one Stockfish dev-version at the moment, when the testrun of that Stockfish dev-version was finished).