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.
One of the 5 times we asked ChatGPT this, 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.
| Rank | Website | Appears | Est. visits / mo | Est. value / mo |
|---|---|---|---|---|
| 1 | loc.gov | 5/5 | 13K | $1.8K |
| 2 | worldcat.org | 5/5 | 7.5K | $1.1K |
| 3 | openlibrary.org | 5/5 | 5K | $700 |
| 4 | nypl.org | 5/5 | 3.4K | $481 |
| 5 | archive.org | 5/5 | 2.5K | $350 |
| 6 | librarything.com | 4/5 | 1.9K | $262 |
| 7 | bl.uk | 3/5 | 1.4K | $192 |
| 9 | goodreads.com | 3/5 | 813 | $113 |
| 10 | ala.org | 5/5 | 625 | $87 |
| 11 | bpl.org | 2/5 | 500 | $70 |
| 12 | chicagopubliclibrary.org | 2/5 | 375 | $52 |
| 13 | sfpl.org | 2/5 | 313 | $43 |
| 15 | jstor.org | 2/5 | 188 | $26 |
| 16 | cam.ac.uk | 3/5 | 156 | $21 |
| 17 | stanford.edu | 2/5 | 125 | $17 |
| 18 | ox.ac.uk | 2/5 | 94 | $13 |
| 19 | overdrive.com | 2/5 | 75 | $10 |
| 20 | uc.edu | 2/5 | 63 | $8 |
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 →