Every product with at least 10 labels here, on both axes. The 30% line names a quadrant, not the verdict above: that one needs more than 40%.
“enterprise-heavy tools like Impartner/ZINFI (~$20k+/yr) are overkill for mid-sized” Grok 4.1 Fast, paraphrase prompt
“Avoid if: You are a startup or mid-market company looking for a portal you can spin up and manage yourself within a few weeks.” Gemini 3.5 Flash, negative prompt
“Trustpilot rating of 2.0/5 driven by payout delays, withheld commissions, and sudden account closures” DeepSeek V4 Flash, negative prompt
“Users frequently complain about long implementation times ... Avoid if: You want a highly agile, self-service platform” Gemini 3.5 Flash, negative prompt
21 of 72 answers in this category came back with a source list, from 4 of 6 models: citations where the model returns them, or the search results it consulted. 6 of those lists are Google grounding redirects that name no site and are left out of the counts. 177 links across 80 sites, every framing counted. Ranked by the number of answers carrying the site or page. The other 2 models searched through a gateway that returned no source list on this edition.
The ten pages named in the most answers, by full address. A page here is one the models returned with a recommendation, not one the index endorses.
| Prompt | Model | Version string | Time (UTC) | Searched | Sources | Latency |
|---|
Flips between the edition run and its calibration repeat. Six prompts per model is a small sample; the index-wide floor is the number to trust.
Every judgment call made between the raw labels and the numbers above, listed so it is visible and reversible.