The FFO endgame test suite is a common benchmark for endgame searching. Computer completely solves each testcase, and find the best move. This benchmark evaluates the exact time for searching and the speed (NPS: Nodes Per Second).
| No. | Depth | Best Move | Score | Time (sec) | Nodes | NPS |
|---|---|---|---|---|---|---|
| #40 | 20 | a2 | +38 | 0.016 | 13095826 | 818489125 |
| #41 | 22 | h4 | +0 | 0.054 | 31733978 | 587666259 |
| #42 | 22 | g2 | +6 | 0.066 | 49405340 | 748565757 |
| #43 | 23 | c7 | -12 | 0.149 | 118010790 | 792018724 |
| #44 | 23 | d2 | -14 | 0.041 | 18079308 | 440958731 |
| #45 | 24 | b2 | +6 | 0.291 | 322619250 | 1108657216 |
| #46 | 24 | b3 | -8 | 0.134 | 90700458 | 676869089 |
| #47 | 25 | g2 | +4 | 0.1 | 88624182 | 886241820 |
| #48 | 25 | f6 | +28 | 0.218 | 157234062 | 721257165 |
| #49 | 26 | e1 | +16 | 0.464 | 399676639 | 861372066 |
| #50 | 26 | d8 | +10 | 0.947 | 755470579 | 797751403 |
| #51 | 27 | e2 | +6 | 0.432 | 386349187 | 894326821 |
| #52 | 27 | a3 | +0 | 0.483 | 403634351 | 835681886 |
| #53 | 28 | d8 | -2 | 2.562 | 2519470056 | 983399709 |
| #54 | 28 | c7 | -2 | 3.984 | 3983373384 | 999842716 |
| #55 | 29 | g6 | +0 | 12.398 | 11082195535 | 893869618 |
| #56 | 29 | h5 | +2 | 1.404 | 1017876893 | 724983542 |
| #57 | 30 | a6 | -10 | 3.098 | 2871440500 | 926869109 |
| #58 | 30 | g1 | +4 | 1.827 | 1556662686 | 852032121 |
| #59 | 34 | h4 | +64 | 0.054 | 17365258 | 321578851 |
| All | - | - | - | 28.722 | 25883018262 | 901156544 |
Without speedup by SIMD
| No. | Depth | Best Move | Score | Time (sec) | Nodes | NPS |
|---|---|---|---|---|---|---|
| #40 | 20 | a2 | +38 | 0.029 | 13745836 | 473994344 |
| #41 | 22 | h4 | +0 | 0.089 | 32685564 | 367253528 |
| #42 | 22 | g2 | +6 | 0.117 | 51731192 | 442146940 |
| #43 | 23 | c7 | -12 | 0.242 | 114425926 | 472834404 |
| #44 | 23 | d2 | -14 | 0.069 | 18898575 | 273892391 |
| #45 | 24 | b2 | +6 | 0.506 | 317687190 | 627840296 |
| #46 | 24 | b3 | -8 | 0.203 | 84792202 | 417695576 |
| #47 | 25 | g2 | +4 | 0.089 | 24700626 | 277535123 |
| #48 | 25 | f6 | +28 | 0.407 | 195897969 | 481321791 |
| #49 | 26 | e1 | +16 | 0.677 | 327109235 | 483174645 |
| #50 | 26 | d8 | +10 | 1.733 | 788308775 | 454881001 |
| #51 | 27 | e2 | +6 | 1.088 | 634944238 | 583588454 |
| #52 | 27 | a3 | +0 | 0.826 | 407859964 | 493777196 |
| #53 | 28 | d8 | -2 | 4.27 | 2456352890 | 575258288 |
| #54 | 28 | c7 | -2 | 6.384 | 3801732457 | 595509470 |
| #55 | 29 | g6 | +0 | 20.773 | 11459161935 | 551637314 |
| #56 | 29 | h5 | +2 | 2.391 | 1041524297 | 435601964 |
| #57 | 30 | a6 | -10 | 4.686 | 2579060408 | 550375673 |
| #58 | 30 | g1 | +4 | 3.607 | 1855300695 | 514361157 |
| #59 | 34 | h4 | +64 | 0.089 | 17164869 | 192863696 |
| All | - | - | - | 48.275 | 26223084843 | 543202172 |
Edax 4.4 is one of the best Othello AI in the world.
If I set the game from the very beginning, same line appears a lot. To avoid this, I set the game from many different near-draw lines.
I used XOT for its testcases.
No opening books used.
If Egaroucid Win Ratio is over 0.5, then Egaroucid wins more than Edax do. "Black" and "White" means Egaroucid played black/white. In all conditions, Egaroucid is stronger than Edax.
| Level | Egaroucid win | Draw | Edax Win | Egaroucid Win Ratio |
|---|---|---|---|---|
| 1 | 1217(Black: 589 White: 628) | 47(Black: 17 White: 30) | 736(Black: 394 White: 342) | 0.62 |
| 5 | 1189(Black: 599 White: 590) | 108(Black: 54 White: 54) | 703(Black: 347 White: 356) | 0.622 |
| 10 | 904(Black: 500 White: 404) | 236(Black: 120 White: 116) | 860(Black: 380 White: 480) | 0.511 |
| 15 | 232(Black: 128 White: 104) | 94(Black: 43 White: 51) | 174(Black: 79 White: 95) | 0.558 |
| 21 | 81(Black: 49 White: 32) | 60(Black: 30 White: 30) | 59(Black: 21 White: 38) | 0.555 |