Max reasoning seemed to get stuck for me too. My default is Medium which seems to work pretty well both in tight and longer running loops.
In your real world experience outside of the benchmarks hows this performing compared to Opus 5? Asking because 5 was so horrible for me I switched back to 4.8.
Max reasoning seemed to get stuck for me too. My default is Medium which seems to work pretty well both in tight and longer running loops.
In your real world experience outside of the benchmarks hows this performing compared to Opus 5? Asking because 5 was so horrible for me I switched back to 4.8.