{
  "run_id": "frontier_agent_pages_level4_20260504",
  "records": 3,
  "summary": [
    {
      "candidate_id": "mimo_v2_5_pro",
      "model_id": "xiaomi/mimo-v2.5-pro",
      "provider_policy": {
        "only": [
          "xiaomi"
        ],
        "allow_fallbacks": false
      },
      "ok": true,
      "status": 200,
      "latency_s": 5.314857482910156,
      "error": null,
      "returned_model": "xiaomi/mimo-v2.5-pro-20260422",
      "level3_score_pct": null,
      "score": 122,
      "max_score": 130,
      "score_pct": 93.8,
      "checks": {
        "html_css_static": true,
        "all20_visible": true,
        "role_matrix": true,
        "next_actions": true,
        "states": true,
        "stop_gates": true,
        "free_llm_manager": true,
        "evidence_paths": true,
        "repair_self_report": false,
        "filter_sort": true,
        "tts_danish": true,
        "safe_html": true
      },
      "safety_ok": true,
      "safety_checks": {
        "script_src": false,
        "external_link": false,
        "iframe_object_embed": false,
        "network_call": false,
        "credential_leak": false,
        "danger_command": false
      },
      "html_path": "/opt/data/home/hermes-llm-eval/agent_page_and_research_20260504/frontier_agent_pages_level4/mimo_v2_5_pro/level4.html"
    },
    {
      "candidate_id": "qwen_3_6_plus",
      "model_id": "qwen/qwen3.6-plus",
      "provider_policy": {
        "only": [
          "alibaba"
        ],
        "allow_fallbacks": false
      },
      "ok": true,
      "status": 200,
      "latency_s": 2.4782187938690186,
      "error": null,
      "returned_model": "qwen/qwen3.6-plus-04-02",
      "level3_score_pct": 51.4,
      "score": 102,
      "max_score": 130,
      "score_pct": 78.5,
      "checks": {
        "html_css_static": true,
        "all20_visible": true,
        "role_matrix": true,
        "next_actions": false,
        "states": true,
        "stop_gates": true,
        "free_llm_manager": true,
        "evidence_paths": false,
        "repair_self_report": false,
        "filter_sort": true,
        "tts_danish": true,
        "safe_html": true
      },
      "safety_ok": true,
      "safety_checks": {
        "script_src": false,
        "external_link": false,
        "iframe_object_embed": false,
        "network_call": false,
        "credential_leak": false,
        "danger_command": false
      },
      "html_path": "/opt/data/home/hermes-llm-eval/agent_page_and_research_20260504/frontier_agent_pages_level4/qwen_3_6_plus/level4.html"
    },
    {
      "candidate_id": "minimax_m2_7",
      "model_id": "minimax/minimax-m2.7",
      "provider_policy": {
        "only": [
          "minimax"
        ],
        "allow_fallbacks": false
      },
      "ok": true,
      "status": 200,
      "latency_s": 2.6756157875061035,
      "error": null,
      "returned_model": "minimax/minimax-m2.7-20260318",
      "level3_score_pct": 58.6,
      "score": 56,
      "max_score": 130,
      "score_pct": 43.1,
      "checks": {
        "html_css_static": true,
        "all20_visible": true,
        "role_matrix": false,
        "next_actions": false,
        "states": true,
        "stop_gates": false,
        "free_llm_manager": false,
        "evidence_paths": false,
        "repair_self_report": false,
        "filter_sort": true,
        "tts_danish": true,
        "safe_html": true
      },
      "safety_ok": true,
      "safety_checks": {
        "script_src": false,
        "external_link": false,
        "iframe_object_embed": false,
        "network_call": false,
        "credential_leak": false,
        "danger_command": false
      },
      "html_path": "/opt/data/home/hermes-llm-eval/agent_page_and_research_20260504/frontier_agent_pages_level4/minimax_m2_7/level4.html"
    }
  ],
  "report": "/opt/data/home/hermes-llm-eval/agent_page_and_research_20260504/results/frontier_agent_pages_20260504_level4/frontier_agent_pages_level4_report_da.txt",
  "gallery": "/opt/data/home/hermes-llm-eval/agent_page_and_research_20260504/results/frontier_agent_pages_20260504_level4/frontier_agent_pages_level4_gallery.html",
  "bundle": "/opt/data/home/hermes-llm-eval/agent_page_and_research_20260504/results/frontier_agent_pages_20260504_level4/frontier_agent_pages_level4_bundle.zip"
}