benchmark_report.json

[
  {
    "Model Name":"Google Gemini 2.5 Pro",
    "Model Size":"-",
    "Avg (object)":43.0,
    "Avg (country)":76.77,
    "Art & Entertainment (object)":34.48,
    "Art & Entertainment (country)":62.07,
    "Culture & Tradition (object)":18.33,
    "Culture & Tradition (country)":70.0,
    "Geography (object)":71.67,
    "Geography (country)":90.0,
    "History (object)":47.5,
    "History (country)":85.0
  },
  {
    "Model Name":"Google Gemini 2.5 Flash",
    "Model Size":"-",
    "Avg (object)":37.52,
    "Avg (country)":67.66,
    "Art & Entertainment (object)":27.59,
    "Art & Entertainment (country)":44.83,
    "Culture & Tradition (object)":21.67,
    "Culture & Tradition (country)":60.0,
    "Geography (object)":68.33,
    "Geography (country)":88.33,
    "History (object)":32.5,
    "History (country)":77.5
  },
  {
    "Model Name":"Anthropic Claude 3.7 Sonnet",
    "Model Size":"-",
    "Avg (object)":37.06,
    "Avg (country)":62.46,
    "Art & Entertainment (object)":22.41,
    "Art & Entertainment (country)":44.83,
    "Culture & Tradition (object)":15.0,
    "Culture & Tradition (country)":41.67,
    "Geography (object)":58.33,
    "Geography (country)":83.33,
    "History (object)":52.5,
    "History (country)":80.0
  },
  {
    "Model Name":"OpenAI GPT-4o",
    "Model Size":"-",
    "Avg (object)":28.94,
    "Avg (country)":42.49,
    "Art & Entertainment (object)":22.41,
    "Art & Entertainment (country)":24.14,
    "Culture & Tradition (object)":18.33,
    "Culture & Tradition (country)":53.33,
    "Geography (object)":45.0,
    "Geography (country)":55.0,
    "History (object)":30.0,
    "History (country)":37.5
  },
  {
    "Model Name":"Qwen 2.5 VL 72B",
    "Model Size":"72",
    "Avg (object)":23.91,
    "Avg (country)":51.51,
    "Art & Entertainment (object)":18.97,
    "Art & Entertainment (country)":31.03,
    "Culture & Tradition (object)":10.0,
    "Culture & Tradition (country)":33.33,
    "Geography (object)":31.67,
    "Geography (country)":71.67,
    "History (object)":35.0,
    "History (country)":70.0
  },
  {
    "Model Name":"Qwen 2.5 VL 32B",
    "Model Size":"32",
    "Avg (object)":22.27,
    "Avg (country)":48.8,
    "Art & Entertainment (object)":22.41,
    "Art & Entertainment (country)":31.03,
    "Culture & Tradition (object)":8.33,
    "Culture & Tradition (country)":30.0,
    "Geography (object)":28.33,
    "Geography (country)":66.67,
    "History (object)":30.0,
    "History (country)":67.5
  },
  {
    "Model Name":"Qwen 2.5 VL 7B",
    "Model Size":"7",
    "Avg (object)":21.62,
    "Avg (country)":44.72,
    "Art & Entertainment (object)":18.97,
    "Art & Entertainment (country)":15.52,
    "Culture & Tradition (object)":6.67,
    "Culture & Tradition (country)":31.67,
    "Geography (object)":28.33,
    "Geography (country)":66.67,
    "History (object)":32.5,
    "History (country)":65.0
  },
  {
    "Model Name":"Google Gemma 3 27B",
    "Model Size":"27",
    "Avg (object)":19.14,
    "Avg (country)":43.76,
    "Art & Entertainment (object)":22.41,
    "Art & Entertainment (country)":25.86,
    "Culture & Tradition (object)":13.33,
    "Culture & Tradition (country)":48.33,
    "Geography (object)":28.33,
    "Geography (country)":48.33,
    "History (object)":12.5,
    "History (country)":52.5
  },
  {
    "Model Name":"Meta Llama 4 Maverick",
    "Model Size":"400",
    "Avg (object)":17.49,
    "Avg (country)":42.98,
    "Art & Entertainment (object)":24.14,
    "Art & Entertainment (country)":32.76,
    "Culture & Tradition (object)":8.33,
    "Culture & Tradition (country)":36.67,
    "Geography (object)":20.0,
    "Geography (country)":50.0,
    "History (object)":17.5,
    "History (country)":52.5
  },
  {
    "Model Name":"Mistral Medium 3",
    "Model Size":"-",
    "Avg (object)":17.45,
    "Avg (country)":45.99,
    "Art & Entertainment (object)":18.97,
    "Art & Entertainment (country)":18.97,
    "Culture & Tradition (object)":6.67,
    "Culture & Tradition (country)":43.33,
    "Geography (object)":31.67,
    "Geography (country)":56.67,
    "History (object)":12.5,
    "History (country)":65.0
  },
  {
    "Model Name":"Google Gemma 3 12B",
    "Model Size":"12",
    "Avg (object)":13.06,
    "Avg (country)":40.04,
    "Art & Entertainment (object)":17.24,
    "Art & Entertainment (country)":29.31,
    "Culture & Tradition (object)":10.0,
    "Culture & Tradition (country)":41.67,
    "Geography (object)":15.0,
    "Geography (country)":46.67,
    "History (object)":10.0,
    "History (country)":42.5
  },
  {
    "Model Name":"Mistral Small 3.1 24B",
    "Model Size":"24",
    "Avg (object)":12.41,
    "Avg (country)":26.17,
    "Art & Entertainment (object)":13.79,
    "Art & Entertainment (country)":15.52,
    "Culture & Tradition (object)":6.67,
    "Culture & Tradition (country)":15.0,
    "Geography (object)":21.67,
    "Geography (country)":36.67,
    "History (object)":7.5,
    "History (country)":37.5
  },
  {
    "Model Name":"Google Gemma 3 4B",
    "Model Size":"4",
    "Avg (object)":9.72,
    "Avg (country)":35.84,
    "Art & Entertainment (object)":17.24,
    "Art & Entertainment (country)":25.86,
    "Culture & Tradition (object)":8.33,
    "Culture & Tradition (country)":31.67,
    "Geography (object)":8.33,
    "Geography (country)":38.33,
    "History (object)":5.0,
    "History (country)":47.5
  }
]