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)→
More from Models
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27