Early rbench results show Claude Opus 5.5 pass rate drops ~50% from xhigh to max thinking level
Rasmic · x · 2026-11-15
Early rbench benchmark results from Rasmic show Claude Opus 5.5 loses nearly 50% of its pass rate when switching from xhigh to max thinking level. The shared charts also show max mode costs $6.19 per task at 17.9 median minutes, versus $2.82 at xhigh, while GPT-5.1 hits 80–86.7% at $0.43/task. His take: "You should almost never use max level... like ever" — with the caveat that the bench is very early.
More from coding & agent
- Blender MCP hits 34.5k stars: direct 3D modeling in plain language with any LLM — sidahuj · 2026-11-15
- 18 agents coding overnight on one Linux box: 'I'm the bottleneck now' — AIOSAI · 2026-11-15
- IBM Engineer on Trustworthy AI Evals: Calibrate LLM Judges, Check Agent Trajectories — TejasKumar_ · 2026-11-15
- Antigravity Browser Agent Swarm Turns a Portrait Into Google Sheets Pixel Art — Saboo_Shubham_ · 2026-11-15
- CrommaCode launches: a gamified desktop terminal for watching Claude Code and Codex work — huangyun_122 · 2026-11-15
- MCP server + Ollama drives Final Cut Pro: 30-min video rough cut in under 5 minutes — Technovangelist · 2026-11-15