Same prompt on Opus. ~$5.
I’d pay the extra ~$2.
GPT-5.6 gave Opus 5 and Grok 4.6 a question: each generate a draft of a Three.js 18-second future racing helmet product advertisement.
Then GPT-5.6 thinks that Opus is slightly better. Can this result be believed? No subjective color?
Opus 5 + higgsfield: $20.
That's all it took to destroy a $60 billion industry. Not a company. The entire industry. not disrupt. not challenge. destroy. $60 billion in web design revenue and the whole thing folds to a number you'd spend on lunch. → HOW A $60 BILLION
Fable 5.1 has landed on RamenBench!
It's a HUGE upgrade over Fable 5, and dethrones Opus 5 for the top spot imo It did take noticeably longer than Fable 5, but the results are worth the wait Check out the other models here
You have reached the end of the archive
All of Claude Opus 5