leaderboard.json

{
  "entries": [
    {
      "model_name": "Llama 3.1 8B (baseline)",
      "factual_recall": 0.71,
      "socratic_dialogue": 0.68,
      "misconception_trap": 0.58,
      "overall": 0.657,
      "timestamp": "2026-04-06 17:10 UTC"
    },
    {
      "model_name": "Random agent",
      "factual_recall": 0.18,
      "socratic_dialogue": 0.22,
      "misconception_trap": 0.1,
      "overall": 0.167,
      "timestamp": "2026-04-06 17:10 UTC"
    },
    {
      "model_name": "Test Model pytest",
      "factual_recall": 0.75,
      "socratic_dialogue": 0.68,
      "misconception_trap": 0.6,
      "overall": 0.677,
      "timestamp": "2026-04-25 18:36 UTC"
    }
  ]
}