Hacker News Reader

The benchmark appears to have a mistake, as Opus 5 and Fable 5 score 53.4% and 53.5%, respectively, for the Agentic Coding row (FrontierCode v1.1). But Opus 5 is the highlight.

View on HN

How hard can it be to be to correctly annotate the table? DeepSWE doesn’t have a highlight either; Fable slightly better than Opus (69.7% vs 68.8%).

Reply on news.ycombinator.com