Users joke Claude Opus 5 feels like GPT-5 as Anthropic touts SOTA scores

ChengleiSi · x · 2026-07-25

A reply thread jokes that Opus 5 feels like GPT-5, while the quoted Anthropic post says the model is now state of the art on several coding and knowledge-work evaluations.

The attached image appears to show only a tiny gap between two benchmark values, reinforcing the tone of benchmark-driven one-upmanship around frontier models.

Related event: Claude Opus 5 Sparks Debate as Anthropic Highlights SOTA(3 posts)→

Original post →

More from Models

Models channel →