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
7s
Input Tokens
5968
Output Tokens
139
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. Her symptoms included an annoying cough for a few days, chest pain when lying down, and mild fever, which later worsened to include chills, dizziness, and pleuritic chest pain.