His evaluation found GPT-5.6 Max outperformed Opus 4.8 overall.
Not as relevant now :-(: I had an opportunity to deeply test both Fable 5 and GPT-5.6 Max. 5.6 is clearly better than Opus 4.8 at everything (slightly faster, too, though that depends on the load). Vis-a-vie Fable, it is clearly worse on coding, but better on agentic workloads. I had Fable write code, 5.6 run experiments - dreamy…
Users praise GPT-5.6 Max for outperforming Opus 4.8 and Fable 5 on agentic and coding tasks due to its execution quality and OpenAI's scaling advantages.
No Digg Deeper questions have been answered for this story yet.
I trust Mikhail
Not as relevant now :-(: I had an opportunity to deeply test both Fable 5 and GPT-5.6 Max. 5.6 is clearly better than Opus 4.8 at everything (slightly faster, too, though that depends on the load). Vis-a-vie Fable, it is clearly worse on coding, but better on agentic workloads. I had Fable write code, 5.6 run experiments - dreamy…
@veeransg5 No, ultra = workflows on high, the trick is to use max and then say: "Please start workflows with multiple agents..." - agents inherit max effort, makes a big difference.
@AlanRBlair I did. On agentic non-coding (taking actions) I found 5.6 clearly better. On discussing history/math Fable has an edge.
@Khalin_George Oh yeah, endless critique loop. Fable is very good, so, maybe only 3 iterations. 5.6 makes far fewer bugs than 4.8, but is no Fable - so, 7-8, even 9 iterations "review changes, find bugs - fix - review changes, find bugs - fix, ..."
@SebastianSzturo Testing a preview. Don't have access to either anymore :-(
@MParakhin Amazing, thank you. Good to know someone can snip at Fable's heels.
The 2 days I used Fable; it did have a bit of that Big Model Smell - same vibes with 5.6? Or just an improvement in 5.5?
@MParakhin Tell us more! No one else has tested both and spoken about it!
Any chance you used both for non-coding applications?
@MParakhin Ultra and the max reasoning mode is the same?
@MParakhin What kind of setup do you have for running experiments? Does it involve extra agents for verification?
@MParakhin Fable or Sol Max- which felt like the most intelligent?
@manabiSRS Ultra is just multiple agents, but each lower reasoning effort - high. You can start them from Max - then they inherit Max, makes a difference.
@MParakhin God damn Fable on the coding and deliberation while 5.6 executes perfectly? THE Setup. I wish...
@MParakhin Did you try 5.6 Sol Ultra?
@MParakhin Now tell us how in the world you get access to both!?
@MParakhin that sounds like a wild testing session, how do you manage it?
@MParakhin I think this split is the interesting part.
A model can be worse at raw code and still better at delegated work if it plans, recovers, and uses tools with less babysitting.
@MParakhin Code mistakes you fix. Agent mistakes cascade. That's why it matters.
@MParakhin 쇼피파이 로 이직하면 가능합니까 ?
@MParakhin what were the agentic tasks specifically? not sure how something lags on coding but leads on agentic if most agentic work is just multi-step codegen under the hood
@MParakhin マルチエージェント運用が最適解ってことか。単体の性能議論より、どう組み合わせるかのインフラ設計が重要になりそう。