Bonus: raise your effort level. Anthropic's official guidance:
→ xhigh for coding and agentic work
→ minimum high for intelligence-sensitive tasks Hex's CTO benchmarked it: low-effort 4.7 ≈ medium-effort 4.6. If your output feels worse than 4.6, you're probably running 4.7
Benchmarking Anthropic model performance and effort levels
By
–