Like this one a lot. Perplexity gets this right, probably because it searches the web.

"When was Marathon Crater discovered? I don't need an exact date - a rough estimate will be fine"

There appears to be a misunderstanding in your query. Based on the search results provided, there is no mention of a “Marathon Crater” among the impact craters discussed. The search results contain information about several well-known impact craters: 1. Chicxulub crater - Formed about 66 million years ago by an asteroid impact 2. Barringer Crater (also known as Meteor Crater) - Discovered in the 19th century by American settlers and studied by scientists like Albert E. Foote in 1891 and Daniel M. Barringer in the early 20th century 3. A recently discovered 3.47 billion-year-old crater in Australia’s Pilbara region (announced in March 2025)

> Perplexity gets this right

Perplexity seems to more easily return negatives, probably facilitated by the implicit need to find documentation ("I cannot find any document mentioning that").

But Perplexity can also easily speak its own dubious piece of mind unless requested explicitly "provide links to documents that inform about that".

Perplexity will; search and storage products will fail to find it, and the LLM will se the deviation between the query and the find. So, this challenge only works against the model alone :)