OpenAI just dropped something huge – the full O3 model, the O4 Mini series, and a brand new coding agent called Codex CLI. In this video, we test them all. From vision tasks to reasoning and real-world coding, this release marks a major step forward in generative AI. Are these the tools that finally rival GitHub Copilot and Cursor? Let’s explore benchmarks, performance, pricing, and whether you should switch to Codex CLI today.
🔗 Relevant Links
Models: https://openai.com/index/introducing-...
Windsurf News: https://www.reuters.com/technology/ar...
❤️ More about us
Radically better observability stack: https://betterstack.com/
Written tutorials: https://betterstack.com/community/
Example projects: https://github.com/BetterStackHQ
📱 Socials
Twitter: / betterstackhq
Instagram: / betterstackhq
TikTok: / betterstack
LinkedIn: / betterstack
📌 Chapters:
0:00 Buying Windsurf
0:18 Intro
0:32 o3 Demo
3:20 o3 coding demo
3:39 o4-mini coding demo
3:52 3.7 Sonnet Comparison
4:07 CLI Coding Tool
6:25 Benchmarks
7:29 Pricing
