Opus 5 is shown as a new Pareto-optimal LLM with strong ARC-AGI-3 results

brandon_galang · x · 2026-07-25

A post says there is a new Pareto-optimal LLM in Opus 5.

The attached chart focuses on ARC-AGI-3 novel problem solving versus total evaluation cost. It shows Opus 5 (high) at roughly 30.2% novel problem-solving score, while Opus 4.8 (high) is shown far lower, alongside cost comparisons that frame the model as much stronger but also expensive to evaluate.

Related event: Anthropic Releases Claude Opus 5(57 posts)→

Original post →

More from Models

Models channel →