We've switched the default model in playcode.io among Opus 4.8, Opus 4.6, Sonnet 4.6, and Sonnet 5. I must admit, Opus 4.8 is quite expensive, and the costs accumulate quickly. Opus 4.6 is about 50% cheaper, while Sonnet 5 is significantly more affordable. According to the data, Sonnet 5 is about 2-3 times cheaper. Fable 5 is unaffordable at all...

Today, I tested Sol 5.6 on various tasks. It performs similarly to Opus 4.8 but is still noticeably more expensive than Sonnet 5. Although Sonnet 5 isn't the top model, it's quite effective for creating typical websites for small and medium businesses. However, they will increase the price starting September 1, as their free offer is ending.

I'm also actively testing Grok 4.5. There's something promising about it. The design is mediocre, in my opinion, but it operates quickly and reliably without any deadloops. Usually, Grok models would fail or loop, but this one is stable.

Overall, I really want a benchmark based on real tasks.