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.

Duration

10s

Input Tokens

7762

Output Tokens

309

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

Melisa Farrow talked on the phone with medical staff (nurse who would relay to the doctor) on 2025-05-20 at 08:12. Her symptoms during the phone call were:

1. Chills
2. Increased pain when breathing
3. Left side aching when coughing
4. Feeling dizzy
5. Fever of 38.5°C (which she had checked at home)

She called because she had woken up feeling worse than the previous day, despite initially saying she felt okay during her first visit. This phone call led to an immediate urgent care appointment where she was subsequently diagnosed with community-acquired pneumonia and admitted to the hospital.