Many people have reported Opus 4.6 is a step back from Opus 4.5 - that 4.6 is consuming 5-10x as many tokens as 4.5 to accomplish the same task: https://github.com/anthropics/claude-code/issues/23706 I haven't seen a response from the Anthropic team about it. I can't help but look at Sonnet 4.6 in the same light, and want to stick with 4.5 across the board until this issue is acknowledged and resolved.
Opus 4.6 has been a hit-and-miss for me. It does extremely well on very complex, long-running tasks but also struggles with very basic, seemingly straightforward work and often provides conflicting recommendations. For example, just this morning Opus 4.6 provided two options, recommended option 1, and at the end of the same message asked to start option 2; this does not happen in Opus 4.5.
For now, my workflow will be for everyday tasks claude-opus-4-5 and opus 4.6 for more complex work.