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.

Context Reasoning – mistral/mistral-large-eu Task | Opper AI

Input Tokens

0

Output Tokens

0

Duration

0

Cost

0

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

Melisa Farrow was diagnosed with acute community-acquired pneumonia in the left lower lobe, with pleuritic chest pain secondary to the infection. She was admitted to Danderyds Sjukhus - Internal Medicine Ward for treatment, which included IV Cefotaxime, oral Doxycycline, Paracetamol, IV fluids, and oxygen therapy. Her condition improved, and she was discharged on 2025-05-23 with a prescription for Amoxicillin-clavulanate and Paracetamol. A final check-up on 2025-05-30 confirmed her full recovery.