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.

100
Duration
22s
Input Tokens
5889
Output Tokens
269
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 who talked on the phone with a doctor was Melisa Farrow. During a phone call on 2025-05-20 at 08:12, Melisa reported to a nurse that she woke up feeling worse, had chills, increased pain when breathing, left-sided chest pain especially when coughing, dizziness, and a fever of 38.5°C. These symptoms were suggestive of an infection, which was later confirmed as acute community-acquired pneumonia (left lower lobe) with pleuritic chest pain.