Surge AI Benchmark: Higher Thinking Effort Beat Every Coding Agent Harness Tested
rseroter · x · 2026-11-10
Surge AI benchmarked popular coding-agent setups (Opus 5.5 in Claude Code, sudo L7 benchmark). Vanilla Claude Code at xhigh thinking gained +11.3 over baseline at 3.5x cost, beating Superpowers (+2.4), /goal +/code-review (+3.3), and Compound Engineering (+1.8 at 8x cost). A 37-skill harness spawning 17 review agents still missed that a confirmation email leaked a Zoom passcode to unpaid registrants. Takeaway: elaborate harness bureaucracies often add less than simply raising thinking effort.
More from coding & agent
- InstructGPT co-author's Jev harness PDF promises 200x faster, 400x cheaper coding agents — Redo · 2026-11-10
- Three coding-agent security patches ship this week: Mistral Vibe, Jan, DeepSeek Harness — alvelda · 2026-11-10
- Dev rewrote Node app in Go, asks why developer-friendly languages matter when AI writes code — rakyll · 2026-11-10
- Claude Fable 5.2 Lands in Factory: Works Through Diagnostics, Keeps Precision — matanSF · 2026-11-10
- Open-Source MCP Lets AI Agents Edit Your YC Application Directly via GraphQL — arthurcolle · 2026-11-10
- verity-gate 0.2.0 ships its agent action-vetting gate as MCP servers for pip and npm — W1RELESS · 2026-11-10