The user compares GPT-5.3 Codex and Sonnet models within OpenClaw, finding Sonnet significantly supe

Testing & DebugπŸ“… 2026/04/04
Source@pbteja1998
#Developer#GitHub#Low Risk#Manual Trigger#Reusable#Semi-Automatic#代码仓库#δ»£η η”Ÿζˆ#ζŠ₯ε‘Š#ζ¨‘εž‹θ―„ζ΅‹
Tried GPT 5.3 Codex with @openclaw, and it's so bad... 

and it also is giving me the famous... "If you want, I'll now...." thing at the end 😡

Not sure what's the best model to use with @openclaw now... 

I started a new session and asked that same question to Sonnet, it's response is easily 10x better.