Context Reasoning

Context understanding and reasoning tasks test accurate answers grounded in provided context. This capability is essential for knowledge-base support bots, policy lookup systems, and internal knowledge Q&A applications. Models are evaluated on their ability to provide accurate answers that are properly grounded in the given context rather than hallucinating information.

50
Duration
8s
Input Tokens
5889
Output Tokens
218
Cost
$0.00
Context
Input
Which patient talked on the phone with a doctor, and what were their symptoms?
Expected output
Melisa Farrow, who had 38.5°C fever, cough, her left side hurts, has pain when breathing and feels dizzy
Model output
The patient Melisa Farrow talked on the phone with a nurse, reporting worsening symptoms including fever, chest pain, and difficulty breathing. Her symptoms and subsequent clinical findings indicated she was experiencing community-acquired pneumonia, with evidence of lung infection and pleuritis.