Pulling ahead? Depends on the usecase I guess. 3 turns into a very basic Gemini-CLI session and Gemini 3 Pro has already messed up a simple `Edit` tool-call. And it's awfully slow. In 27 minutes it did 17 tool calls, and only managed to modify 2 files. Meanwhile Claude-Code flies through the same task in 5 minutes.
Knowing Googles MO, its most likely not the model but their harness system that's the issue. God they are so bad at their UI and agentic coding harnesses...
I think Claude is genuinely much smarter, and more lucid.
Yeah - agree, Anthropic much better for coding. I'm more thinking about the 'average chat user' (the larger potential userbase), most of whom are on chatgpt.