Post claims Grok 4.5 is 37× more token-efficient than Opus 5

ns123abc · x · 2026-07-28

A post claims Grok 4.5 is 37× more token-efficient than Opus 5, citing a chart comparing the two on the exact same prompt.

The quoted reply is skeptical, noting that the comparison is based on one-shot long-horizon prompts and may not reflect real-world use. Still, the claim is the kind of model-efficiency comparison people will argue about quickly.

Related event: Grok 4.5 Token-Efficiency Claims Draw Scrutiny(2 posts)→

Original post →

More from Models

Models channel →