Smarter models spawn far more subagents: 0.90 rank match, ~5x gap
airesearch12 · x · 2026-11-02
An Artificial Analysis chart shared by Adam Holtererer shows a strong correlation between model intelligence and subagent spawning in coding: 0.90 rank match (Spearman over 8 models). Per 100 T3 Code turns, GPT-6 Astra and Opus 5.5 spawn 14.6 subagents vs 3 for GPT-6 Luna, Haiku 5.5 and Gemini 3.8 Flash — roughly a 5x gap. Smarter models apparently decompose tasks and fan out subagents far more aggressively.
More from coding & agent
- Astral founder: foundational open source projects could be supplanted by agent-built alternatives — charliermarsh · 2026-11-02
- Bot Platform Shootout: Grok Bot Beats OpenAI Dots, ChatGPT Work, Claude and Muse on Every Measure — elonmusk · 2026-11-02
- Agent coding's underrated perk: an append-only, contextualized log of your project's history — vboykis · 2026-11-02
- EVOLV: open-source AI that rewrites its own code, builds its own tools, and evolves locally — Sea_Manufacturer6590 · 2026-11-02
- asc CLI: open-source Go binary automates App Store releases with 1,200+ API endpoints — rudrank · 2026-11-02
- thdxr: Many pre-AI opinions on programming simply stopped mattering — charliermarsh · 2026-11-02