Claude Opus 4.6 scored 86.8% on BrowseComp with a multi-agent harness. Without it? Lower. The architecture gap is the story, not the model. Full breakdown on AdwaitX. 🔗 #ClaudeAI #AIAgents #AdwaitX #Dev2026
adwaitx.com
Claude’s Agent Harness Patterns Are Rewriting Developer Assumptions About What AI Can Handle Alone
That’s Anthropic’s confirmed BrowseComp score for Claude Opus 4.6 running with a multi-agent harness, web search, compaction triggered at 50,000 tokens, and max reasoning effort.