Skip to content

Latest commit

 

History

History
59 lines (58 loc) · 6.79 KB

2025-01-10-llama3.2-vision-11b-instructor-results.md

File metadata and controls

59 lines (58 loc) · 6.79 KB

Benchmark Results (model=llama3.2-vision:11b, date=2025-01-10)

Domain Response Model Sample Response JSON
document.invoice Invoice 
{
  "invoice_id": null,
  "period_start": null,
  "period_end": null,
  "invoice_issue_date": null,
  "invoice_due_date": null,
  "order_id": null,
  "customer_id": null,
  "issuer": null,
  "issuer_address": null,
  "customer": null,
  "customer_email": null,
  "customer_phone": null,
  "customer_billing_address": null,
  "customer_shipping_address": null,
  "items": null,
  "subtotal": null,
  "tax": null,
  "total": null,
  "currency": null,
  "notes": null
}
document.receipt Receipt 
❌
document.resume Resume 
❌
document.us-drivers-license USDriversLicense 
❌
document.utility-bill UtilityBill 
{
  "account_number": null,
  "date_mailed": null,
  "service_for": null,
  "service_address": {
    "street": null,
    "city": null,
    "state": null,
    "zip_code": null
  },
  "billing_period_start": null,
  "billing_period_end": null,
  "date_due": null,
  "amount_due": 88.14,
  "previous_balance": null,
  "payment_received": null,
  "current_charges": null,
  "breakdown_of_charges": [
    {
      "description": "Electricity",
      "amount": 50.0,
      "usage": null,
      "rate": null
    },
    {
      "description": "Water",
      "amount": 20.0,
      "usage": null,
      "rate": null
    }
  ],
  "payment_options": [
    "Check",
    "Online Payment"
  ],
  "contact_information": {
    "phone_number": "+1-800-123-4567"
  }
}
document.w2-form W2Form 
{
  "control_number": null,
  "ein": null,
  "ssn": null,
  "employee_name": "Anastasia Hodges",
  "employee_address": {
    "street": null,
    "city": null,
    "state": null,
    "zip_code": null
  },
  "employer_name": null,
  "employer_address": {
    "street": null,
    "city": null,
    "state": null,
    "zip_code": null
  },
  "wages_tips_other_compensation": 0.0,
  "federal_income_tax_withheld": 0.0,
  "social_security_wages": 0.0,
  "social_security_tax_withheld": 0.0,
  "medicare_wages_and_tips": 0.0,
  "medicare_tax_withheld": 0.0,
  "tax_year": null
}
aerospace.remote-sensing RemoteSensing 
❌
healthcare.medical-insurance-card MedicalInsuranceCard 
{
  "provider_service": {
    "provider_service_number": null,
    "precertification_number": null
  },
  "member_information": {
    "member_name": "John Doe",
    "member_id": "1234567890",
    "group_number": "ABC123"
  },
  "pharmacy_plan": {
    "rx_bin": null,
    "rx_pcn": null,
    "rx_grp": null,
    "pharmacy_help_desk": null
  },
  "insurance_provider": {
    "provider_name": "Blue Cross Blue Shield",
    "network": "PPO"
  },
  "coverage": {
    "office_visit": null,
    "specialist_visit": null,
    "urgent_care": null,
    "emergency_room": null,
    "inpatient_hospital": null
  }
}
retail.ecommerce-product-caption RetailEcommerceProductCaption 
❌
media.tv-news TVNews 
{
  "description": "Biden criticises Netanyahu in an interview",
  "chyron": null,
  "network": "CNN",
  "reporters": null
}
media.nfl-game-state NFLGameState 
{
  "description": null,
  "teams": [
    {
      "name": "GB",
      "score": null
    },
    {
      "name": "AZ",
      "score": 7
    }
  ],
  "status": "in_progress",
  "quarter": 2,
  "clock_time": "14:56",
  "possession_team": "GB",
  "down": "1st",
  "distance": null,
  "yard_line": null,
  "network": null,
  "is_shown": true
}
media.nba-game-state NBAGameState 
{
  "description": null,
  "teams": [
    {
      "name": "MIA",
      "score": 7
    },
    {
      "name": "SA",
      "score": 6
    }
  ],
  "status": "in_progress",
  "quarter": 1,
  "clock_time": "9:09",
  "shot_clock": null,
  "network": "ESPN",
  "is_shown": true
}