GPT 5.6 Ultra better in Claude Code than in Codex?

Developer Theo reports that GPT-5.6 Ultra performs better in Anthropic's Claude Code than in OpenAI's Codex, expressing frustration over the discrepancy.

Theo - t3.gg @theo gpt-5.6-sol is meaningfully better in Claude Code than in Codex I'm going to crash out so badly over this 2:58 AM · Jul 11, 2026 162K Views