{
  "accuracy": 0.9979,
  "f1_weighted": 0.9979,
  "f1_macro": 0.9979,
  "n_eval": 484,
  "confusion_matrix": [
    [
      44,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      44,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      0,
      44,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      0,
      0,
      44,
      0,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      0,
      0,
      0,
      44,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      0,
      0,
      0,
      0,
      44,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      0,
      0,
      0,
      0,
      0,
      44,
      0,
      0,
      0,
      0
    ],
    [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      43,
      1,
      0,
      0
    ],
    [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      44,
      0,
      0
    ],
    [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      44,
      0
    ],
    [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      44
    ]
  ],
  "classes": [
    "QA",
    "Summary",
    "Coding",
    "Reasoning",
    "Agentic",
    "Creative",
    "Translation",
    "Classification",
    "Extraction",
    "Long-context",
    "Fast/simple"
  ]
}