Opper

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.

Input Tokens

Output Tokens

Duration

Cost

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

On 2025-05-20 at 09:10, Melisa Farrow was re-examined due to worsening symptoms. Her temperature was 38.8°C, pulse was 102 bpm, respiratory rate was 22/min, and O2 saturation was 93% on room air. She appeared pale, visibly unwell, and experienced pleuritic chest pain. Auscultation revealed clear crackles in the left lower lobe (LLL) with slightly diminished breath sounds in the same area. Percussion confirmed dullness. Her CRP was 98 mg/L, WBC was 13.7 x10^9/L, and neutrophils were 9.6 x10^9/L. A chest X-ray confirmed an infiltrate in the left lower lobe with mild pleural effusion, consistent with community-acquired pneumonia. She was admitted to Danderyds Sjukhus for further treatment.