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.

0
Duration
14s
Input Tokens
8275
Output Tokens
166
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 with the ID Oscar Jansson was diagnosed with mild persistent asthma, likely triggered by a viral upper respiratory infection. He was prescribed an inhaled corticosteroid, a short-acting beta-agonist, and an antipyretic as needed.