{
  "model": "novus-demo-1",
  "created": "2026-01-01",
  "suite": "mini-eval",
  "results": [
    {
      "task": "sentiment",
      "metric": "accuracy",
      "score": 0.912,
      "n": 500
    },
    {
      "task": "ner",
      "metric": "f1",
      "score": 0.874,
      "n": 300
    },
    {
      "task": "summarization",
      "metric": "rougeL",
      "score": 0.381,
      "n": 200
    },
    {
      "task": "translation_en_es",
      "metric": "bleu",
      "score": 0.336,
      "n": 400
    },
    {
      "task": "qa_extractive",
      "metric": "exact_match",
      "score": 0.685,
      "n": 350
    }
  ]
}
