SUDOKU BENCHMARK ยท BEYOND

Claude Fable 5.1 on Beyond grid 3

Solved: 56 of 56 blank cells right. It said it was 99% sure. All of Claude Fable 5.1's answers.

RESULTSolved
CELLS RIGHT56 / 56
SAID99% sure
MODEL TIME8.4 min
COST$2.59 (API-equivalent)
TOKENS IN / OUT912 / 51,505

5 given 5 filled correctly 53 wrong, with the right digit 3 left empty

The end of its reply

<grid>
285769143
134528976
967413825
673941258
852376491
419852637
796134582
341285769
528697314
</grid>
<confidence>99</confidence>

Grid beyond-2 of set v1, 25 givens. Puzzle as one line: ......1....4..8..6.6...3.2.......25.8.2..6.9.....5...7..613..8.3...8.7..52...7...