Opus 5.5 is a "token destroyer": highest per-task token usage of any benchmarked model

ivan_bezdomny · x · 2026-09-23

User benchmarks show the new Opus 5.5's main drawback is extreme token consumption: it uses the most tokens per Intelligence Index task of any model benchmarked, which explains the accompanying price cut — cheaper per token, but usage may eat the savings. Multiple users are calling it a "token DESTROYER".

Original post →

More from Models

Models channel →