{
 "source_file": "locomo_results_20261021_024242.json",
 "metadata": {
  "benchmark": "locomo",
  "project_name": "hoploco_g5",
  "run_id": "hoploco_g5",
  "timestamp": "20261021_024242",
  "answerer_model": "openai/gpt-5",
  "judge_model": "openai/gpt-5",
  "provider": "openai",
  "top_k": 200,
  "top_k_cutoffs": [
   "top_50"
  ],
  "total_questions": 1540,
  "categories": [
   1,
   2,
   3,
   4
  ],
  "evaluate_only": true
 },
 "metrics_by_cutoff": {
  "top_50": {
   "overall": {
    "total": 1540,
    "correct": 1421,
    "accuracy": 92.27272727272727,
    "avg_score": 92.27272727272727
   },
   "by_category": {
    "multi-hop": {
     "total": 282,
     "correct": 257,
     "accuracy": 91.13475177304964,
     "avg_score": 91.13475177304964
    },
    "open-domain": {
     "total": 96,
     "correct": 78,
     "accuracy": 81.25,
     "avg_score": 81.25
    },
    "single-hop": {
     "total": 841,
     "correct": 785,
     "accuracy": 93.34126040428062,
     "avg_score": 93.34126040428062
    },
    "temporal": {
     "total": 321,
     "correct": 301,
     "accuracy": 93.76947040498442,
     "avg_score": 93.76947040498442
    }
   }
  }
 }
}