Exact prompt sent to every model
Below is a small-business bank statement as text with a running balance column and a few multi-line descriptions that wrap. Extract: account_last4, statement_period {start, end}, opening_balance, closing_balance, transactions (array of {date, description (single line, trimmed), amount (negative for debits), balance_after, category}) where category is one of "deposit","card","ach","check","fee", "transfer","other" inferred from the description. Verify that opening_balance plus the sum of amounts equals closing_balance and include "reconciles": true|false and "reconcile_difference". Return only the JSON.
A private fixture (biz-extract-04/statement.txt) 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.