Claude Opus 5 vs Gemini 4 vs GPT-6 Astra vs Grok 4.6
I handed the same unfinished drawing to four different AI models and said "be creative." Rumoured Gemini 4 checkpoint is inside Arena. four completely different pandas came out. and I genuinely can't pick a favorite 👇
They built an AI agent in 20 minutes and sold it to Anthropic for $100k - and at Stanford showed how to repeat it from scratch
02:00 - how to build your first agent with Opus 5 in 20 minutes 22:34 - one agent replaces an Anthropic engineering team worth $200k a year 49:47 -
Zero excess reasoning opus 5 low drone worker bee mode via properly designed skill / mcp tool call loop.
Been a real PITA this week, late nights and weekends we're getting true opus 5 low, weekdays we're getting routed to sonnet. sonnet will reason and discuss and prod and mess
GPT-6 Astra doesn’t look slightly better here—it looks a full generation ahead.
The drawing comes together far more naturally. Gemini 4 and Opus 5 never really close the gap. In this test, OpenAI looks almost untouchable. Is Astra really that far ahead?
You have reached the end of the archive
All of Claude Opus 5