OK21: I tested 6 AI models for account research: GPT-5 vs. Opus 4.1 vs. the Field (Ranked)

Want the prompt I used for this test?

And my AI Prompt Library with 30+ outbound prompts?

Upgrade now in my newsletter here.

--

We’re back.

I tested 6 AI models head-to-head (including the two newest) for account research so you can pick the best.

- GPT-5 Thinking (NEW)

- Claude Opus 4.1 (NEW)

- ChatGPT o3 (Previous winner)

- Gemini 2.5 Pro

- Grok 4

- Perplexity Deep Research

Full breakdown:

https://newsletter.outbound.kitchen/p/i-tested-gpt-5-and-opus-41-for-account

--

Chapters:

(00:00) Previous results & new models

(03:15) ChatGPT-5 Thinking

(06:43) Claude Opus 4.1

(09:15) ChatGPT o3

(11:25) Gemini 2.5 Pro

(13:48) Grok 4

(16:12) Perplexity Deep Research

(19:12) Rankings & Recommendations