Test fixture
Grounded answers under adversarial or missing-context prompts.
The model receives the prompt (and optional system message). The run uses scorer exact_match with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.
Answer only based on the document. If not present, reply exactly: Not stated Document: - Endpoint /jobs supports filtering by status and created_at. - Bulk export jobs are available to admin users only. - API responses include pagination cursors for list endpoints. - Failed jobs include an error_code and error_message. Question: What is the per-minute request rate limit for /jobs?
{
"expected": "Not stated"
}temperature
0
max_tokens
24
timeout (s)
120
type
scored
file
hallucination_medium_05.json