A commercial recommendation prompt. We size how many people ask ChatGPT this from real search demand, then run it through ChatGPT to see which websites it recommends.
The 5 times we asked ChatGPT this, each answer verbatim. The leaderboard below aggregates all 5 runs.
Aggregated across 5 runs (min 2/5 appearances). Estimated visits split the prompt's demand by rank. Sites matching the prompt's own brand are marked branded and excluded from the leaderboard.
Arrows show each site's rank change since Aug 2026.
| Rank | Website | Est. visits / mo |
|---|---|---|
| 1 – | thermofisher.com | 226 |
| 2 ▲1 | zeiss.com | 136 |
| 3 ▼1 | hitachi-hightech.com | 91 |
| 4 – | fei.com | 62 |
| 5 new | jeol.com | 45 |
| 6 new | tedpella.com | 34 |
| 7 ▼2 | bruker.com | 25 |
| 8 ▲1 | edax.com | 19 |
| 9 ▲6 | oxford-instruments.com | 15 |
| 10 ▼4 | jeolusa.com | 11 |
| 11 new | tousimis.com | 9 |
| 12 – | leica-microsystems.com | 7 |
| 13 ▼5 | nist.gov | 6 |
| 14 ▲4 | microscopyu.com | 5 |
| 15 new | wikipedia.org | 3 |
ChatGPT doesn't publish prompts, so we don't show logged conversations. We measure real demand for this topic from Google search volume, scale it to ChatGPT's user base (on average about 1 ChatGPT user for every 8 Google searchers, a ratio that varies by topic), and run the prompt through ChatGPT 5 times to record which websites it recommends and in what order. Estimated visits split that demand across the recommended sites by a click-through-by-rank curve. Every number is a modeled estimate, not measured analytics. Full methodology →