Model chart pits Opus 5, Sonnet 5 and GPT-5.6 against cost and coding scores

haider1 · x · 2026-07-27

A post argues that Opus 5 is significantly more cost-efficient than Fable 5, while calling Sonnet 5 a poor release because it costs more and uses more tokens than GPT-5.6 Sol.

The attached chart compares several models across intelligence, coding, and agentic indices, along with cost per task and tokens per task. The poster says GPT-5.6 Sol remains the everyday workhorse even compared with Opus 5.

Original post →

More from Models

Models channel →