Loading video player...
Anthropic released Claude Opus 4.6 claiming the top spot on Terminal Bench 2.0, but OpenAI fired back with GPT 5.3 Codex literally minutes later and beat it by over 10%. I had to test both on real coding tasks ā¤ļø More about us Radically better observability stack: https://betterstack.com/ Written tutorials: https://betterstack.com/community/ Example projects: https://github.com/BetterStackHQ š± Socials Twitter: https://twitter.com/betterstackhq Instagram: https://www.instagram.com/betterstackhq/ TikTok: https://www.tiktok.com/@betterstack LinkedIn: https://www.linkedin.com/company/betterstack š Chapters: 00:00 Intro 00:42 What's New 02:03 Complex Coding Test 06:02 Club Penguin... 08:33 UI Design 09:55 Benchmarks 10:53 Extra's (Claude Code + Codex)