Bug Hunt Bench: Sonnet 5.5 max scores 55.5 but costs $134.79 per run

PawelHuryn · x · 2026-09-29

Pawel Huryn added a log-scale score-vs-turns view to Bug Hunt Bench, his blind-graded benchmark of frontier coding models on 105 real planted bugs, and published per-effort numbers for Sonnet 5.5:

For comparison, Sonnet 5 max scored 9 at $17.96. The picture: an extremely motivated model, fast and cheap per turn, but cost scales steeply with effort — max is 3x the score of low at 25x the price. Cost spread across the board is roughly 200x.

Related event: Bug Hunt Bench Launches: Sonnet 5.5 Leads Frontier Coding Models(4 posts)→

Original post →

More from coding & agent

coding & agent channel →