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 | lsac.org | 4/5 | 275 | $742 |
| 2 | lawschool.cornell.edu | 4/5 | 165 | $445 |
| 3 | aba.org | 3/5 | 110 | $297 |
| 4 | law.yale.edu | 3/5 | 76 | $204 |
| 5 | law.stanford.edu | 3/5 | 55 | $148 |
| 6 | lawschooltransparency.com | 2/5 | 41 | $111 |
| 7 | law.harvard.edu | 2/5 | 30 | $81 |
| 8 | law.columbia.edu | 2/5 | 23 | $63 |
| 9 | usnews.com | 2/5 | 18 | $48 |
| 10 | uchicago.edu | 2/5 | 14 | $37 |
| 11 | law.uchicago.edu | 2/5 | 11 | $29 |
| 12 | nyu.edu | 2/5 | 8 | $22 |
| 13 | law.nyu.edu | 2/5 | 7 | $18 |
| 14 | columbia.edu | 2/5 | 6 | $14 |
| 15 | law.duke.edu | 2/5 | 4 | $11 |
| 16 | lawschoolnumbers.com | 2/5 | 3 | $9 |
| 17 | law.berkeley.edu | 2/5 | 3 | $7 |
| 18 | berkeley.edu | 2/5 | 2 | $5 |
| 19 | harvard.edu | 2/5 | 2 | $4 |
| 20 | duke.edu | 2/5 | 1 | $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 →