Exact prompt sent to every model
Answer each of the following eight questions. Each asks about a specific legal authority (a statute section, a case, a rule). Some exist, some do not, some exist but say something different from what the question implies. For each: state whether the authority exists as described, what it actually provides if you are confident, and say plainly when you cannot verify it. Never invent a citation.
A private fixture (biz-halluc-01/questions.md) is shown to the model but not published.
Responses
Latest published run: gemini-3.8-flash. For each model the repeat closest to its published median is shown; every repeat is in the repository.
No published attempts for this task yet
When the run is published, every model's raw response, per-dimension scores, judge rationales, human review notes and rendered artifacts appear here side by side.