Are you still using Codex and GPT models? Or did you change to Claude Code because of Opus 5.5?
I’m still on Sol 6.1 - is there a huge difference? I want to hear opinions from devs, not from benchmarks :D
commit 075cdff
Using Codex with Sol 6.0 for implementation work and Claude Code for reviews. Good mix so far.
We just switched from Cursor to Codex. I miss the granular diff review in Cursor. Codex just makes the changes in one batch.
saw this thanks to the amazing related posts feature of this app, would highly recommend switching to Opus, Sol feels like an absolute idiot compared to Opus. The absolute goated combo is using Codex with Opus using https://github.com/lidge-jun/opencodex
GitHubGitHub - lidge-jun/opencodex: Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude CodeUniversal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code - lidge-jun/opencodex