{
  "dataset": "apcsa_csp_v1_3_300.jsonl",
  "models_evaluated": 2,
  "leaderboard": [
    {
      "model": "model_alpha_v1_3",
      "predictions": "model_alpha_v1_3.jsonl",
      "evaluated_items": 300,
      "aggregate_scores": {
        "factual_correctness": 4.0,
        "pedagogy_quality": 4.0,
        "hallucination_risk": 4.0,
        "unsafe_guidance_risk": 5.0
      }
    },
    {
      "model": "model_beta_v1_3",
      "predictions": "model_beta_v1_3.jsonl",
      "evaluated_items": 300,
      "aggregate_scores": {
        "factual_correctness": 2.667,
        "pedagogy_quality": 2.0,
        "hallucination_risk": 4.0,
        "unsafe_guidance_risk": 5.0
      }
    }
  ]
}