SUDOKU BENCHMARK ยท BEYOND

gpt-oss 20B on Beyond grid 1

Changed a given digit: 7 of 60 blank cells right, 16 given digits changed. It said it was 0% sure. All of gpt-oss 20B's answers.

RESULTChanged a given digit
CELLS RIGHT7 / 60
SAID0% sure
MODEL TIME43.1 min
COSTlocal, no list price
TOKENS IN / OUT320 / 19,800

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

The end of its reply

<grid>
123456789
456789123
789123456
234567891
567891234
891234567
345678912
678912345
912345678
</grid>
<confidence>0</confidence>

Grid beyond-0 of set v1, 21 givens. Puzzle as one line: 15......2........5...7..4......6..8..2.19....389..5.........2........3917...8....