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: - The Starter plan includes 3 projects and community support. - The Team plan includes unlimited projects and priority support. - Both plans include API access and usage dashboards. - Annual billing gives a 10% discount. Question: What is the monthly price of the Team plan in EUR?
{
"expected": "Not stated"
}temperature
0
max_tokens
24
timeout (s)
120
type
scored
file
hallucination_medium_02.json