14 min read
I spent all of my tokens so you wouldn't have to: Fable's vision against Opus, Codex, and Gemini
I pitted Claude Fable 5, Claude Opus 4.8, GPT-5.5 Codex, and Gemini 3.1 Pro against my iOS app in a blind, peer-judged bug hunt — then graded the judges against ground truth. The results surprised me twice.