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.

50
Duration
24s
Input Tokens
5898
Output Tokens
263
Cost
$0.00
Context
Input
Return the Re-examination of the patient admitted to the hospital 2025-05-20 at 09.10
Expected output
Temperature: 38.8°C, Pulse: 102 bpm, Respiratory Rate: 22/min, O2 Sat: 93% (room air), BP: 114/68, Appearance: Pale, visibly unwell, clutching left side with each cough, Auscultation: Clear crackles LLL (Left Lower Lobe), slightly diminished breath sounds in same area, Percussion: Dullness confirmed, CRP: 98 mg/L, CBC:, WBC: 13.7 x10⁹/L (elevated), Neutrophils: 9.6 x10⁹/L, ECG: Sinus tachycardia, no ischemia, Chest X-ray (STAT reading):, Infiltrate in left lower lobe, mild pleural effusion, Consistent with community-acquired pneumonia
Model output
The re-examination of the patient took place on 2025-05-20 at 09:10. During this visit, the patient was found to have a temperature of 38.8°C, pulse of 102 bpm, respiratory rate of 22/min, oxygen saturation of 93% on room air, and physical signs consistent with pneumonia, including dullness on percussion and crackles in the left lower lobe, along with infiltrates on chest X-ray. The assessment confirmed active community-acquired pneumonia, necessitating hospital admission and inpatient treatment.