Skip to content

Latest commit

 

History

History
59 lines (58 loc) · 11.4 KB

2025-01-10-gpt-4o-2024-11-20-instructor-results.md

File metadata and controls

59 lines (58 loc) · 11.4 KB

Benchmark Results (model=gpt-4o-2024-11-20, date=2025-01-10)

Domain Response Model Sample Response JSON
document.invoice Invoice 
{
  "invoice_id": "9999999",
  "period_start": null,
  "period_end": null,
  "invoice_issue_date": "2023-11-11",
  "invoice_due_date": null,
  "order_id": null,
  "customer_id": null,
  "issuer": "LOGO GOES HERE",
  "issuer_address": {
    "street": "123 Main Street",
    "city": "Anytown",
    "state": "US",
    "postal_code": "01234",
    "country": null
  },
  "customer": "Fred Davis",
  "customer_email": "info@invoice.com",
  "customer_phone": "(800) 123-4567",
  "customer_billing_address": {
    "street": "1335 Martin Luther King Jr Ave",
    "city": "Dunedin",
    "state": "FL",
    "postal_code": "34698",
    "country": null
  },
  "customer_shipping_address": {
    "street": "249 Windward Passage",
    "city": "Clearwater",
    "state": "FL",
    "postal_code": "33767",
    "country": null
  },
  "items": [
    {
      "description": "Service",
      "quantity": 1,
      "currency": null,
      "unit_price": 200.0,
      "total_price": 200.0
    },
    {
      "description": "Parts AAA",
      "quantity": 1,
      "currency": null,
      "unit_price": 100.0,
      "total_price": 100.0
    },
    {
      "description": "Parts BBB",
      "quantity": 2,
      "currency": null,
      "unit_price": 50.0,
      "total_price": 100.0
    }
  ],
  "subtotal": 400.0,
  "tax": null,
  "total": 400.0,
  "currency": null,
  "notes": null
}
document.receipt Receipt 
{
  "receipt_id": "70CSCB10738BP",
  "transaction_date": "2021-01-26T22:36:26",
  "merchant_name": "Walmart",
  "merchant_address": {
    "street": "8060 W Tropical Pkwy",
    "city": "Las Vegas",
    "state": "NV",
    "postal_code": "89149",
    "country": null
  },
  "merchant_phone": "702-839-3620",
  "cashier_name": "Sarah",
  "register_number": "35",
  "customer_name": null,
  "customer_id": null,
  "items": [
    {
      "description": "Boys Crew",
      "quantity": 1.0,
      "unit_price": 9.48,
      "total_price": 9.48
    },
    {
      "description": "Boys Socks",
      "quantity": 1.0,
      "unit_price": 6.97,
      "total_price": 6.97
    },
    {
      "description": "Boxer Brief",
      "quantity": 1.0,
      "unit_price": 10.98,
      "total_price": 10.98
    }
  ],
  "subtotal": 27.43,
  "tax": 2.3,
  "total": 29.73,
  "currency": "USD",
  "payment_method": {
    "type": "Debit",
    "card_last_4": null,
    "card_type": "US Debit"
  },
  "discount_amount": null,
  "discount_description": null,
  "tip_amount": null,
  "return_policy": null,
  "barcode": "5455 5110 5197 3924 8502",
  "additional_charges": null,
  "notes": "Low Prices You Can Trust. Every Day.",
  "others": {
    "terminal_id": "SC162890",
    "approval_code": "817522",
    "network_id": "0056",
    "reference_number": "120800300965"
  }
}
document.resume Resume 
❌
document.us-drivers-license USDriversLicense 
{
  "issuing_state": "MT",
  "license_number": "0812319684104",
  "full_name": "Brenda Lynn Sample",
  "first_name": "Brenda",
  "middle_name": "Lynn",
  "last_name": "Sample",
  "address": {
    "street": "123 Main Street",
    "city": "Helena",
    "state": "MT",
    "zip_code": "59601"
  },
  "date_of_birth": "1968-08-04",
  "gender": "F",
  "height": "5'06\"",
  "weight": 150.0,
  "eye_color": "BRO",
  "hair_color": null,
  "issue_date": "2015-02-15",
  "expiration_date": "2023-08-04",
  "license_class": "D",
  "donor": null,
  "veteran": null
}
document.utility-bill UtilityBill 
{
  "account_number": "1234567890-1",
  "date_mailed": "2019-09-07",
  "service_for": "SPARKY JOULE",
  "service_address": {
    "street": "12345 ENERGY CT",
    "city": null,
    "state": null,
    "zip_code": null
  },
  "billing_period_start": null,
  "billing_period_end": null,
  "date_due": "2019-09-28",
  "amount_due": 88.14,
  "previous_balance": 91.57,
  "payment_received": -91.57,
  "current_charges": 88.14,
  "breakdown_of_charges": [
    {
      "description": "Current PG&E Electric Delivery Charges",
      "amount": 55.66,
      "usage": null,
      "rate": null
    },
    {
      "description": "Silicon Valley Clean Energy Electric Generation Charges",
      "amount": 32.48,
      "usage": null,
      "rate": null
    }
  ],
  "payment_options": [
    "www.pge.com/waystopay"
  ],
  "contact_information": {
    "phone": "1-800-743-5000",
    "hours": "Monday-Friday 7 a.m.-9 p.m., Saturday 8 a.m.-6 p.m.",
    "website": "www.pge.com/MyEnergy"
  }
}
document.w2-form W2Form 
{
  "control_number": "GNI851",
  "ein": "63-0065650",
  "ssn": "554-03-0876",
  "employee_name": "Anastasia Hodges",
  "employee_address": {
    "street": "200 2nd Street NE",
    "city": "Waseca",
    "state": "MN",
    "zip_code": "56093"
  },
  "employer_name": "NORTH 312",
  "employer_address": {
    "street": "151 N Market Street",
    "city": "Wooster",
    "state": "OH",
    "zip_code": "44691"
  },
  "wages_tips_other_compensation": 23677.7,
  "federal_income_tax_withheld": 2841.32,
  "social_security_wages": 24410.0,
  "social_security_tax_withheld": 1513.42,
  "medicare_wages_and_tips": 24410.0,
  "medicare_tax_withheld": 353.95,
  "tax_year": 2020
}
aerospace.remote-sensing RemoteSensing 
{
  "description": "The satellite image shows a large port area with extensive infrastructure for shipping and logistics, adjacent to a densely populated urban area. The port includes container storage, docks, and industrial facilities, while the urban area features residential and commercial buildings.",
  "objects": [
    "shipping containers",
    "docks",
    "industrial facilities",
    "residential buildings",
    "commercial buildings",
    "roads",
    "ships",
    "marina",
    "beach"
  ],
  "categories": [
    "port",
    "residential-area",
    "industrial-area",
    "beach"
  ],
  "is_visible": true
}
healthcare.medical-insurance-card MedicalInsuranceCard 
{
  "provider_service": null,
  "member_information": {
    "member_name": "Member Name",
    "member_id": "XYZ123456789",
    "group_number": "023457"
  },
  "pharmacy_plan": {
    "rx_bin": "987654",
    "rx_pcn": null,
    "rx_grp": null,
    "pharmacy_help_desk": null
  },
  "insurance_provider": {
    "provider_name": "BlueCross BlueShield",
    "network": "PPO"
  },
  "coverage": {
    "office_visit": "$15",
    "specialist_visit": "$15",
    "urgent_care": null,
    "emergency_room": "$75",
    "inpatient_hospital": null
  }
}
retail.ecommerce-product-caption RetailEcommerceProductCaption 
{
  "description": "The Kindle Paperwhite features a 6.8-inch display with adjustable warm light, offering a larger screen and enhanced reading experience.",
  "rating": 90,
  "name": "Kindle Paperwhite (8 GB)",
  "brand": "Amazon",
  "category": "Electronics / E-readers",
  "price": "$139.99",
  "color": "Black"
}
media.tv-news TVNews 
{
  "description": "A news anchor is presenting a story in a studio setting with a blurred background. The chyron displays a headline about Biden criticizing Netanyahu in an interview.",
  "chyron": "Biden criticises Netanyahu in an interview",
  "network": "BBC News",
  "reporters": null
}
media.nfl-game-state NFLGameState 
{
  "description": "Green Bay Packers vs. Arizona Cardinals game in progress.",
  "teams": [
    {
      "name": "GB",
      "score": 0
    },
    {
      "name": "AZ",
      "score": 7
    }
  ],
  "status": "in_progress",
  "quarter": 2,
  "clock_time": "12:12",
  "possession_team": "GB",
  "down": "2nd",
  "distance": 10,
  "yard_line": 10,
  "network": "NBC",
  "is_shown": true
}
media.nba-game-state NBAGameState 
{
  "description": "NBA Finals Game 1 between Miami Heat and San Antonio Spurs.",
  "teams": [
    {
      "name": "MIA",
      "score": 7
    },
    {
      "name": "SA",
      "score": 6
    }
  ],
  "status": "in_progress",
  "quarter": 1,
  "clock_time": "9:09",
  "shot_clock": 11,
  "network": "ESPN",
  "is_shown": true
}