Grok 4.5 Reportedly Nears Opus Level
billyuchenlin · x · 2026-07-13
Reports indicate that Grok 4.5 has reached Opus-level performance in browser usage scenarios and even surpassed GPT-5.6-Sol in one evaluation, bringing it close to Opus.
The post also notes that due to high cached input costs, the overall cost is only about 10% cheaper than Opus, though it is slightly faster. This indicates a model advancement focused on "benchmarking against high-end capabilities."
Related event: Grok 4.5 First Tests: Faster, Cheaper, and Entering Coding Workflows(8 posts)→
More from Models
- A 2-minute Astra audit at low setting wiped a Plus user's full 5-hour limit — Existing-Slide7395 · 2026-09-07
- DeepMind-Princeton paper shows LLMs causally use confidence to decide whether to answer — GoogleDeepMind · 2026-09-07
- Qwen 3.8 Next Flash is painfully verbose: 13-minute thinking on single coding prompts — Infinite-Local5435 · 2026-09-07
- Philosopher asks GPT-6 to review his Oxford book: result rivals top-journal reviews — anselm · 2026-09-07
- Leaker claims xAI is preparing Grok 4.7, hints at another surprise — mark_k · 2026-09-07
- Local LLMs now near Opus-level — what's still keeping them behind closed models? — mrsalvadordali · 2026-09-07