Claude Opus 5 xhigh: ~28m · ~170K tokens · ~$4.60 Qwen 3.8 Max: ~35m · ~50K · ~$0.60

GPT-5.6 Sol: ~19m · ~22.5K · ~$0.68 Grok 4.6 xhigh: 23:48 · 113K · $0.68

Fede(URU) 🇺🇾Aug 22

Opus 5 built a $70k luxury watch product page from one prompt

Fede(URU) 🇺🇾Aug 22

Glm 5.3 didn’t get a new brain — and still jumped past much bigger models.

The weird part is how did it. What changed: → GLM 5.3 uses the same base model as GLM 5.2 → The gains came from post-training focused on coding, long agent tasks, and

Julian Goldie SEOAug 22

One-shot prompt using Opus 5 🤯

Muhammad Hakim 🍉Aug 22