{"type":"post","id":"we-benchmarked-coding-agent-harnesses-thinking-harder-beat-199a68","slug":"we-benchmarked-coding-agent-harnesses-thinking-harder-beat-199a68","title":"We Benchmarked Coding Agent Harnesses. Thinking Harder Beat All of Them.","description":"Surge AI compared four Claude Code harness configurations on 100 software-engineering tasks and found that raising Opus 5.5's thinking effort produced a larger score gain than any tested harness addition.","retrieval_nugget":"Surge AI compared four Claude Code harness configurations on 100 software-engineering tasks and found that raising Opus 5.5's thinking effort produced a larger score gain than any tested harness addition. The result gives teams a useful baseline: before adding orchestration, measure whether it improves the work enough to justify its cost.","published_at":"2026-11-06","updated_at":"2026-11-06","record_date":"2026-11-06","date_kind":"published_at","topics":["claude","claude-code"],"entities":["Surge AI","Claude Code","Opus 5.5","sudo L7","Superpowers","Compound Engineering"],"related_patterns":["harness-architecture-outlives-model-choice"],"novelty_label":"new_fact","what_changed":"A benchmark found that simply asking Claude to think harder outperformed several coding-agent harness setups, including one with 37 skills and 17 agents.","prior_refs":[],"source_url":"https://surgehq.ai/blog/benchmarking-coding-agent-harnesses","source_urls":["https://surgehq.ai/blog/benchmarking-coding-agent-harnesses"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:we-benchmarked-coding-agent-harnesses-thinking-harder-beat-199a68","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/we-benchmarked-coding-agent-harnesses-thinking-harder-beat-199a68/","markdown":"https://newruntime.com/posts/we-benchmarked-coding-agent-harnesses-thinking-harder-beat-199a68.md","json":"https://newruntime.com/posts/we-benchmarked-coding-agent-harnesses-thinking-harder-beat-199a68.json"},"next_reads":[{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/claude-code/","url":"https://newruntime.com/topics/claude-code/","title":"Claude Code","reason":"Explore the claude-code topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude-code.md","json_url":"https://newruntime.com/topics/claude-code.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}