After two months daily-driving Claude Code, one reviewer says Opus 5.5 beats GPT everywhere except computer use
kimmonismus · x · 2026-11-13
Reviewer kimmonismus spent this year alternating between Codex/GPT and Claude Code/Opus, and has used Claude Code + Opus 5.5 as his daily driver for the past two months.
- He calls Opus 5.5 the most efficient and intelligent model to date; GPT is good but not close.
- Claude's biggest weakness is computer use, where he says GPT remains unbeaten.
- Europe seemingly only gets ChatGPT Dot; he's more interested in Claude Duet, also unavailable in Europe. Still hopeful for GPT-6.2, but his current pick is Claude.
More from Models
- OpenAI's 1147-page Yang-Mills proof faces its first expert assessment: not proven yet — mishig25 · 2026-11-13
- Terminal-Bench 4.0 Cost Math: GPT-6.1 Sol Matches Opus 5.5 at ~1/8 the Price — LeadershipNo2904 · 2026-11-13
- HF staffer spotlights basal-2.0-mini, a 1.5B decision-tuned model from Bielik — lhoestq · 2026-11-13
- Observer surprised OpenAI shipped no answer to rival's new model release — jdjohnson · 2026-11-13
- Google's Carbon-Argon-Hydrogen model naming breaks its own size logic — JeremyNguyenPhD · 2026-11-13
- Claude outage: login auth issues hit claude.ai and Claude Code, plus M365 connector errors — op7418 · 2026-11-13