So is it better or worse than Fable 5 on large-scale complexed software engineering tasks (distributed systems, operating systems, high performance computing, compilers, etc. - not frontend stuff)?
WOW! Might also be worth trying the exact task with Kimi K3 to see how much better/worse it is. It was going better than GPT 5.6 Sol Ultra on many large-scale design/SWE tasks.