{
  "model": "sonnet",
  "total_questions": 500,
  "correct": 468,
  "accuracy_pct": 93.6,
  "by_type": {
    "single-session-user": {
      "correct": 70,
      "total": 70,
      "accuracy_pct": 100.0
    },
    "multi-session": {
      "correct": 117,
      "total": 133,
      "accuracy_pct": 88.0
    },
    "knowledge-update": {
      "correct": 75,
      "total": 78,
      "accuracy_pct": 96.2
    },
    "temporal-reasoning": {
      "correct": 126,
      "total": 133,
      "accuracy_pct": 94.7
    },
    "single-session-assistant": {
      "correct": 56,
      "total": 56,
      "accuracy_pct": 100.0
    },
    "single-session-preference": {
      "correct": 24,
      "total": 30,
      "accuracy_pct": 80.0
    }
  },
  "scored_at": "2026-04-15"
}