Comment by YuechenLi
3 hours ago
Fable is just way too expensive and limited compared to GPT 5.6 Sol, and the only task that requires that level of intelligence is frontier scientific research. I use GPT/Codex primarily for coding and usually keep Claude on Sonnet 5 most of the time as I use Claude primarily to debug/brainstorm/make frontends as a supplement to GPT.
I do not agree. Fable is the only model I can leave unattended and give me results for part of my work which is just devops related tasking.
I can hand hold opus but I would rather just ask fable to do it and give me the result that I review and works. Opus will waste tokens and still require me to help nudge it in the right directions.
I think the next gen models from china will put us in a spot that the cost can plummet and I won’t need the Sota from anthropic
I thought Sol was on par with Opus, so comparing it to Fable is apples and (very expensive) oranges?
Sol routinely catches stuff in review that fable misses for me. It's impossible to compare them meaningfully because it's a complete dice roll - but in practice using both in my projects I can get work done with both, and Opus 5 is far more tedious.
But Fable security false positives and pricing just make it not worth compared to Sol IMO.
I've used all three extensively.
Most of the benchmarks have exceeded their usefulness. Opus 5 beats fable 5 on many of them. Anyone who has used both models will notice immediately that this doesn't translate to the real world. Opus 5 is nothing short of a regression from Opus 4.8. Fable is genuinely a great model so long as you don't trigger a guard rail and it downgrades.
Sol in my experience isn't significantly different than fable ignoring that Sol burns usage 10x faster but the end result is hard to differentiate.
GLM 5.3 is a hair behind these two.
An anecdote but not an original one from the people I talk to.
Yeah, it's pretty much apples to oranges, and I don't consider GPT and Claude to be interchangeable at all. From my anecdotal experience, GPTs generally codes more creatively and verbosely but Claudes tend to code more carefully and precisely, so the result is that GPTs generally finds more creative solutions to problems but also writes buggier code, which is why I converged on the setup of GPT/Codex for implementation and Claude for debugging, which feels more like a force multiplier than using each model individually.