Grok 4.5 Shows Strong Software Benchmark Performance

BWay124 · x · 2026-07-13

This post relays/responds to model info regarding Grok 4.5, noting that it is "even slightly higher than Fable" on certain software benchmarks. The author adds that they have used it exclusively for days, despite being a long-time user of Claude Pro Max and Cursor.

While the original post is highly anecdotal, the core focus remains on the model's comparative performance on software benchmarks and the fact that it has entered the stage of real-world usage switching.

Related event: Musk Says Grok 4.5 Beats Fable on Some Coding Benchmarks(3 posts)→

Original post →

More from Models

Models channel →