Grok 4.5 Browser Eval Nears Opus

Kyrannio · x · 2026-07-12

A review of Grok 4.5 shares feedback on browser tasks: its performance is described as surpassing GPT-5.6-Sol and sitting just slightly below Opus.

The post also touches on cost and speed: because cached input is expensive, the overall cost is only about 10% lower than Opus, though it is slightly faster. The author concludes that the competitive landscape now has another "Opus-level" model.

Related event: Grok 4.5 Evaluations: Strong Cost-Performance in Mid-to-High Budgets(5 posts)→

Original post →

More from Models

Models channel →