OpenAI Fan Defends Opus 5.5: Fewer Tokens Per Task, Better Scores Than GPT-6.1 Sol
Angaisb_ · x · 2026-10-06
A self-described OpenAI fan says posts criticizing Opus 5.5 bother him. Objectively, he argues, neither GPT-6 Astra nor GPT-6.1 Sol is smarter than Opus 5.5, and being more efficient doesn't automatically make them better. Calling Opus 5.5 a token-burning machine is an exaggeration: Opus 5.5 high uses fewer tokens per task than GPT-6.1 Sol while scoring better. In a follow-up he notes the screenshot shows more tokens than GPT-6.1 Sol Max, which he forgot to mention.
Related event: OpenAI Fan Defends Claude Opus 5.5 Against Token Cost Criticism(3 posts)→
More from Models
- User Pushes Back on GPT-6 Astra Efficiency Claims, Says Claude Opus 5.5 Limits Feel More Generous — CtrlAltDwayne · 2026-10-06
- Synthetic data is the biggest opportunity in AI coding, argues long thread — creatoroff · 2026-10-06
- Codex spins its wheels while Claude Opus shows far deeper understanding, user reports — iruletheworldmo · 2026-10-06
- Cohere Labs Releases Tiny Aya, a Family of Small Models Covering 70+ Languages — Cohere_Labs · 2026-10-06
- Claude Code auto-resumes after quota resets; full SaaS app cost only 15% of weekly limit — Avntus · 2026-10-06
- User claims Opus 5.5 keeps inserting Anthropic API dependencies into new projects — Former_Technician_60 · 2026-10-06