Skip to content
TriedPrompts

More in Launches, SEO & content.

Stack ChatGPT, Claude and Gemini for a 30-day content test

WorkedEvidence: Described by posterPosted Last checked

Esi Okpoto's 30-day test of ChatGPT, Claude and Gemini on LinkedIn, Instagram and newsletters ended in a three-tool stack.

How to use this

  1. Tap Copy prompt.
  2. Open ChatGPT.
  3. Paste it into the message box.
  4. Send it, then read the answer before acting on it.
New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

Using the same brief, draft this week's LinkedIn post, Instagram caption and email newsletter. Keep brand voice consistent. I will run this identical prompt in ChatGPT, Claude and Gemini to compare ideation, depth and research freshness.

Try this in:

ChatGPT Used in sourceGemini Used in sourceGrok Claude Used in source

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Compare three models on the same content brief, then assign each a standing role in my stack.

Questions to ask me first:
- What brand voice and audience should stay fixed across tools?
- Which three formats are in this test (for example LinkedIn, Instagram, newsletter)?
- How many pieces per format will you score?

Inputs (fill in or confirm):
- Brief: [TOPIC / CTA / VOICE]
- Formats: [LIST]
- Scoring rubric: [IDEATION / DEPTH / FRESHNESS / OTHER]

Rules:
- Keep the prompt text identical across tools.
- Score outputs with the same rubric.
- Don't declare a single winner if stacking is stronger—assign roles.
- Note generic, verbose or stale-research failure modes.

Checkpoint: Agree on the rubric and one sample brief before generating the full batch.

If you get stuck: If a model refuses a format, log it as a miss and continue the others.

Verify before you finish: Confirm every piece used the same brief before scoring.

Output: A score table by tool and format, plus a recommended stack (who does what).

Done when: I know which model owns ideation, depth and trend research.

AI tools

ChatGPTClaudeGemini

Outcome

Esi Okpoto ran a 30-day test with the same prompts across 10 LinkedIn posts, 10 Instagram captions and 10 email newsletters on ChatGPT, Claude and Gemini. Observations: ChatGPT was best for ideation and variety but sometimes generic; Claude was best for depth and nuance but can be verbose; Gemini was best for research-backed content with current information but less creative. Okpoto's winner was not a single model but stacking them—Claude for thought leadership, ChatGPT for creative campaigns, Gemini for trending topics.

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Source

Posted
by Esi Okpoto (LinkedIn)
Last checked
Method:
How we verify

https://www.linkedin.com/posts/esi-okpoto-343322bb_30-days-same-prompts-surprising-winner-activity-7381684938686771201-C6UU

Context: Date estimated from the LinkedIn activity ID. Recreated comparison prompt; the post reports observations rather than quoting one brief.

More in Launches, SEO & content

Similar cases