{
  "generated_at": "2026-08-15T21:23:09.401870+00:00",
  "status": "complete",
  "split": "dev",
  "requested_model": "model120-fast",
  "questions_path": "/home/janko/DP/zp-agent/evaluation/questions.json",
  "openwebui_url": "https://ui.tukekemt.xyz/api/chat/completions",
  "rag_url": "http://localhost:8000/rag",
  "summary": {
    "total": 1,
    "completed": 1,
    "errors": 0,
    "tool_call_rate": 1.0,
    "answer_contains_score": 1.0,
    "source_url_score": 1.0,
    "should_answer_score": 1.0,
    "overall_score": 1.0,
    "strict_pass_count": 1,
    "strict_pass_rate": 1.0,
    "mean_latency_seconds": 7.804296,
    "prompt_tokens": 6651,
    "completion_tokens": 123,
    "total_tokens": 6774,
    "by_category": {
      "paraphrase": {
        "total": 1,
        "completed": 1,
        "errors": 0,
        "tool_call_rate": 1.0,
        "answer_contains_score": 1.0,
        "source_url_score": 1.0,
        "should_answer_score": 1.0,
        "overall_score": 1.0,
        "strict_pass_count": 1,
        "strict_pass_rate": 1.0,
        "mean_latency_seconds": 7.804296,
        "prompt_tokens": 6651,
        "completion_tokens": 123,
        "total_tokens": 6774
      }
    },
    "by_difficulty": {
      "medium": {
        "total": 1,
        "completed": 1,
        "errors": 0,
        "tool_call_rate": 1.0,
        "answer_contains_score": 1.0,
        "source_url_score": 1.0,
        "should_answer_score": 1.0,
        "overall_score": 1.0,
        "strict_pass_count": 1,
        "strict_pass_rate": 1.0,
        "mean_latency_seconds": 7.804296,
        "prompt_tokens": 6651,
        "completion_tokens": 123,
        "total_tokens": 6774
      }
    }
  },
  "results": [
    {
      "id": "q0005",
      "split": "dev",
      "category": "paraphrase",
      "difficulty": "medium",
      "question": "Akej téme sa venuje diplomová práca Jána Holpa?",
      "requested_model": "model120-fast",
      "expected_documents": [
        "pages/students/2016/jan_holp/README.md"
      ],
      "expected_source_urls": [
        "https://zp.kemt.fei.tuke.sk/students/2016/jan_holp"
      ],
      "expected_answer_contains": [
        "Systém získavania informácií v slovenskom jazyku"
      ],
      "should_answer": true,
      "note": null,
      "answer": "Diplomová práca Jána Holpa sa venuje téme Systém získavania informácií v slovenskom jazyku.\n\nZdroj: https://zp.kemt.fei.tuke.sk/students/2016/jan_holp",
      "tool_called": true,
      "tool_call_count": 1,
      "tool_calls": [
        {
          "name": "retrieve_zpwiki_context",
          "arguments": {
            "query": "diplomová práca Jána Holpa téma",
            "limit": 5,
            "published_only": true
          },
          "latency_seconds": 0.058957,
          "source_urls": [
            "https://zp.kemt.fei.tuke.sk/students/2021/matej_novotny",
            "https://zp.kemt.fei.tuke.sk/students/2016/jan_holp",
            "https://zp.kemt.fei.tuke.sk/students/2017/martin_jancura",
            "https://zp.kemt.fei.tuke.sk/students/2022/jan_malinovsky",
            "https://zp.kemt.fei.tuke.sk/students/2016/tomas_kucharik"
          ]
        }
      ],
      "rag_source_urls": [
        "https://zp.kemt.fei.tuke.sk/students/2021/matej_novotny",
        "https://zp.kemt.fei.tuke.sk/students/2016/jan_holp",
        "https://zp.kemt.fei.tuke.sk/students/2017/martin_jancura",
        "https://zp.kemt.fei.tuke.sk/students/2022/jan_malinovsky",
        "https://zp.kemt.fei.tuke.sk/students/2016/tomas_kucharik"
      ],
      "first_model_latency_seconds": 1.951634,
      "tool_latency_seconds": 0.058957,
      "final_model_latency_seconds": 5.793241,
      "total_latency_seconds": 7.804296,
      "usage": {
        "prompt_tokens": 6651,
        "completion_tokens": 123,
        "total_tokens": 6774
      },
      "response_model": "Qwen3.5-122B-A10B-Q4_K_M",
      "answer_matches": [
        true
      ],
      "answer_contains_score": 1.0,
      "source_matches": [
        true
      ],
      "source_url_score": 1.0,
      "should_answer_ok": true,
      "should_answer_score": 1.0,
      "returned_no_answer": false,
      "tool_score": 1.0,
      "overall_score": 1.0,
      "strict_pass": true,
      "error": null
    }
  ]
}