Anyone else surprised that Opus 5 is both stronger and cheaper than Fable? 🤔
I was looking through the newly released benchmark comparison, and one thing stood out immediately.
Opus 5 outperforms Fable 5 on many of the benchmarks that matter to me:
* Agentic terminal coding: 43.3% vs 33.7%
* Knowledge work: 1861 vs 1747
* ARC-AGI-3: 30.2% vs —
* Computer use: 70.6% vs 66.1%
* Business workflows: 26.0% vs 17.4%
Yet from what I’ve seen, the API pricing is also lower than Fable’s.
As someone building AI products, that’s a pretty interesting combination. Usually when a model takes the lead on benchmarks, it’s also the most expensive option.
I’m curious about real-world experience though.
Has anyone here already switched from Fable to Opus 5?
* How does it perform on long coding sessions?
* Is the benchmark advantage noticeable in production?
* Any hidden downsides (latency, tool use, context handling, reliability)?
Would love to hear from people who’ve actually deployed both.
Replies
The benchmark and pricing combination is definitely interesting. But I think the real test is what happens in production, especially with reliability, latency, and how consistently the model handles real workflows over long sessions.
A model can look better on paper and still not be the best fit for every product. I’d be especially interested in hearing from people who have run both models on the same tasks with the same tools and constraints.
I work in Online Reputation Management, so I also think user trust and real-world experiences can sometimes tell a different story from benchmark results. If people consistently have a better experience with one model, that can become just as important as the benchmark advantage.
Has anyone done a direct side-by-side test using the same production workflow?