Claude's new Opus 5 model is out and on most benchmarks it's actually beating Fable. I'm going to talk about why no one saw this coming, when you should use Fable versus Opus, and whether there's still room for models like ChatGPT Sol or open-weight models like Kimi K3.
So Fable 5 has been out for about a month now and it's truly amazing until you run out of usage on the subscription and have to pay the API costs. Opus 5, on the other hand, is a slightly smaller model. And so there's really no reason to think that it would be better than Fable 5.
Across most of the benchmarks, it absolutely is. It also beats ChatGPT Sol across almost every benchmark on both price and performance. Before this release, ChatGPT could at least claim they were the cheaper version of Fable.
Now, not so much. 6 Sol right now. But that doesn't mean that Opus is the only model you should be using.
Fable is still the best model in a lot of important ways. So let me talk about when to use each model and how to use them together. Fable is still the smarter model.
And now you're thinking, TJ, I thought you said Opus beat Fable on most of the benchmarks. And yes, it does. But not because it's smarter.
It's because it never gives up. Fable is incredibly smart, but it knows it's smart, which is why it almost never doubts itself. It plows forward with whatever clever solution it's come up with.
And they are typically quite clever. Opus, on the other hand, doubts itself every step of the way, which is why it double checks and triple checks all of its work.
So here's how you use them together. If you're doing anything simple or straightforward, just use Opus. It's going to end up being cheaper, and it's going to do a great job.
But if you're doing anything complex and important—you're doing something where you need the model to have good taste and judgment— You need it to reason through many different factors and priorities. Then you should use Fable on high effort with one caveat. When you're giving Fable a task, include the extra instruction that you're in charge of design and review, but all implementation should be handled by Opus sub-agents.
Ultimately, you want Fable to come up with the plan and you want Fable to be given the final sign-off. But Opus is actually better at the implementation. And you'll also end up saving a lot of usage this way.
Currently, on Claude subscriptions, you can only use up to 50% of your usage on Fable. I've been working this way for the last three days and only about 30% of my usage is going to Fable. Fable will typically spin up three to six sub-agents that all run Opus.
But TJ, what about all these open source models coming out of China like Kimi K3 that is just as smart and supposedly way cheaper? So Kimi K3 is really impressive and it actually does beat Claude on a few benchmarks, though it still loses on the vast majority to both Opus and Fable. But it's actually not that cheap, at least not yet.
It looks like for now it'll be about half the cost of Opus, but that's if you're paying for usage. If you're on the Claude subscription, Claude is still incredibly affordable. If you're utilizing all your usage on a Claude subscription, you're only paying 4% of the usage cost, which is about 8% of Kimi K3 right now.
And while Fable is only available on the Max plan, Opus is available on the Pro plan. So unless you're an enterprise that's forced to pay for usage, I think Claude's where it's at right now.
