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
19s
Input Tokens
7755
Output Tokens
515
Cost
$0.00
Context
Input
Which patient had to be accepted in the hospital?
Expected output
Melisa Farrow
Model output
Melisa Farrow had to be accepted in the hospital. She was diagnosed with community-acquired pneumonia in the left lower lobe with pleuritic chest pain. After an initial consultation on May 19, 2025, she returned the next day with worsening symptoms including fever of 38.8°C, reduced oxygen saturation (93%), and visible distress. Her chest X-ray confirmed an infiltrate in the left lower lobe with mild pleural effusion. Due to her oxygen saturation, systemic signs, and worsening condition, she was admitted to Danderyds Sjukhus (Internal Medicine Ward) where she received IV antibiotics, fluids, and oxygen therapy for approximately 3 days before being discharged on May 23, 2025.