One-Prompt 3D Test Ranks Opus 5 vs Astra 6: Never Bother With Low Effort
chaseleantj · x · 2026-09-13
Using an identical prompt (a zoomable, rotatable 3D potted dandelion on a white surface, no AGENTS.md or skill), the author ranked four models: 1. Opus 5 low, 2. Opus 5 high, 3. Astra 6 low, 4. Astra 6 high. Conclusion: for extreme quality skip low effort entirely — always use effort >= high — though none of the outputs were very good.
More from coding & agent
- mitsuhiko on agentic coding: over-generating code poisons the agent's own context — mitsuhiko · 2026-09-13
- M3E Canvas turns browser sketches into vibe-coding prompts for Claude Code and Cursor — tom_doerr · 2026-09-13
- 28-Minute Free Video from Claude Code Engineer Covers CLAUDE.md, Memory Shortcuts and Parallel Sessions — nikola_mr64990 · 2026-09-13
- Build a domain-specific agent harness with PowerShell and PSAISuite — dfinke · 2026-09-13
- Mac MCP: open-source MCP server turns ordinary ChatGPT chats into a macOS control plane — bulutarkan · 2026-09-13
- Dad with zero coding experience ships an App Store app after 8 months building it entirely with Claude — BUYMEBONESTOORM · 2026-09-13