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 | 0.031 | 16997628 | 548310580 |
| #41 | 22 | h4 | +0 | 0.071 | 24207723 | 340953845 |
| #42 | 22 | g2 | +6 | 0.103 | 53386603 | 518316533 |
| #43 | 23 | g3 | -12 | 0.173 | 89368561 | 516581277 |
| #44 | 23 | b8 | -14 | 0.081 | 14737343 | 181942506 |
| #45 | 24 | b2 | +6 | 0.417 | 365913891 | 877491345 |
| #46 | 24 | b3 | -8 | 0.184 | 72808508 | 395698413 |
| #47 | 25 | g2 | +4 | 0.09 | 28623049 | 318033877 |
| #48 | 25 | f6 | +28 | 0.357 | 177552046 | 497344666 |
| #49 | 26 | e1 | +16 | 0.427 | 246001308 | 576115475 |
| #50 | 26 | d8 | +10 | 1.635 | 1238528233 | 757509622 |
| #51 | 27 | e2 | +6 | 0.749 | 445087184 | 594241901 |
| #52 | 27 | a3 | +0 | 0.866 | 541177162 | 624915891 |
| #53 | 28 | d8 | -2 | 4.012 | 3195739778 | 796545308 |
| #54 | 28 | c7 | -2 | 4.812 | 4406176438 | 915664263 |
| #55 | 29 | g6 | +0 | 13.025 | 9772271726 | 750270382 |
| #56 | 29 | h5 | +2 | 1.727 | 836776216 | 484525892 |
| #57 | 30 | a6 | -10 | 3.369 | 2322235752 | 689295266 |
| #58 | 30 | g1 | +4 | 2.313 | 1276275073 | 551783429 |
| #59 | 34 | e8 | +64 | 0.459 | 5864536 | 12776766 |
| All | - | - | - | 34.901 | 25129728758 | 720028903 |
Without speedup by SIMD
| No. | Depth | Best Move | Score | Time (sec) | Nodes | NPS |
|---|---|---|---|---|---|---|
| #40 | 20 | a2 | +38 | 0.039 | 15642677 | 401094282 |
| #41 | 22 | h4 | +0 | 0.086 | 23864262 | 277491418 |
| #42 | 22 | g2 | +6 | 0.146 | 54012600 | 369949315 |
| #43 | 23 | c7 | -12 | 0.145 | 43346280 | 298939862 |
| #44 | 23 | b8 | -14 | 0.102 | 16542190 | 162178333 |
| #45 | 24 | b2 | +6 | 0.611 | 365766568 | 598635954 |
| #46 | 24 | b3 | -8 | 0.264 | 91211537 | 345498246 |
| #47 | 25 | g2 | +4 | 0.108 | 25244982 | 233749833 |
| #48 | 25 | f6 | +28 | 0.426 | 146189774 | 343168483 |
| #49 | 26 | e1 | +16 | 0.602 | 260644739 | 432964682 |
| #50 | 26 | d8 | +10 | 2.184 | 1029002849 | 471155150 |
| #51 | 27 | e2 | +6 | 1.198 | 541359040 | 451885676 |
| #52 | 27 | a3 | +0 | 0.898 | 385656725 | 429461831 |
| #53 | 28 | d8 | -2 | 4.844 | 2703465246 | 558105954 |
| #54 | 28 | c7 | -2 | 7.622 | 4862726309 | 637985608 |
| #55 | 29 | g6 | +0 | 19.685 | 10018926638 | 508962491 |
| #56 | 29 | h5 | +2 | 2.359 | 875422326 | 371098908 |
| #57 | 30 | a6 | -10 | 5.299 | 2766188517 | 522020856 |
| #58 | 30 | g1 | +4 | 3.317 | 1351288396 | 407382694 |
| #59 | 34 | e8 | +64 | 0.442 | 5998341 | 13570907 |
| All | - | - | - | 50.377 | 25582499996 | 507821029 |
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 | 1386(Black: 686 White: 700) | 42(Black: 14 White: 28) | 572(Black: 300 White: 272) | 0.704 |
| 5 | 1250(Black: 639 White: 611) | 87(Black: 51 White: 36) | 663(Black: 310 White: 353) | 0.647 |
| 10 | 1041(Black: 571 White: 470) | 237(Black: 117 White: 120) | 722(Black: 312 White: 410) | 0.58 |
| 15 | 473(Black: 248 White: 225) | 192(Black: 84 White: 108) | 335(Black: 168 White: 167) | 0.569 |
| 21 | 81(Black: 48 White: 33) | 60(Black: 28 White: 32) | 59(Black: 24 White: 35) | 0.555 |