{
  "api_version": "1",
  "updated": "2026-11-05",
  "latest_event": "2026-11-04",
  "rights": "© Frontier Log, all rights reserved.",
  "benchmark": {
    "slug": "agents-last-exam-1-1",
    "name": "Agents' Last Exam v1.1",
    "family": "agents-last-exam",
    "unit": "%",
    "higher_is_better": true,
    "status": "active",
    "active": true,
    "superseded_by": null,
    "retired": null,
    "benchmark_url": "https://agents-last-exam.org",
    "introduced": "2026-10-14",
    "creator": "UC Berkeley RDI",
    "introduced_source": "https://github.com/rdi-berkeley/agents-last-exam/blob/9c5e496e70b52ed104b2060bbf1cbd9bb521c0d9/releases/v1.1/assets.json",
    "settings": [
      {
        "setting": "score",
        "name": "Score",
        "url": "https://frontierlog.ai/benchmark/agents-last-exam-1-1",
        "results": 2
      },
      {
        "setting": "unstated",
        "name": "Measure not stated",
        "url": "https://frontierlog.ai/benchmark/agents-last-exam-1-1/unstated",
        "results": 2
      },
      {
        "setting": "cli-unstated",
        "name": "CLI subset, measure not stated",
        "url": "https://frontierlog.ai/benchmark/agents-last-exam-1-1/cli-unstated",
        "results": 1
      },
      {
        "setting": "pass",
        "name": "Pass rate",
        "url": "https://frontierlog.ai/benchmark/agents-last-exam-1-1/pass",
        "results": 1
      }
    ]
  },
  "total": 1,
  "results": [
    {
      "id": "hy4:agents-last-exam-1-1:pass:1",
      "model": "hy4",
      "model_name": "Hy4",
      "model_date": "2026-11-04",
      "event": "https://frontierlog.ai/event/2026-11-04-hy4",
      "benchmark": "agents-last-exam-1-1",
      "benchmark_name": "Agents' Last Exam v1.1",
      "setting": "pass",
      "setting_name": "Pass rate",
      "score": 41.0,
      "unit": "%",
      "printed": "41.0",
      "reported_by": "tencent",
      "run_by": null,
      "label": "Hy4",
      "source": "https://hy.tencent.ai/research/hy4",
      "source_title": "Introducing Hy4",
      "source_date": "2026-11-04",
      "where": "'Appendix: benchmark results' table image, row 'Agents' Last Exam v1.1 (Pass Rate)', column 'Hy4'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "harness and subset not stated; highest reasoning setting",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-11-05",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/8fc24d0f588e6069.jpg",
      "source_image_original": "https://hy-model-ap-prod-1258344703.cos.ap-guangzhou.myqcloud.com/llm-blog/default/9a5ea02f/2026110402023072_85b416b6484a88ef96ef6edda563b560.jpg?q-sign-algorithm=sha1&q-ak=AKIDRl074nOsGdJ9zjMsCRWP3ShmgS3VtX4S&q-sign-time=1793728954;2109088954&q-key-time=1793728954;2109088954&q-header-list=&q-url-param-list=&q-signature=747236201b67dd4e9872ed806c8de224d0ca57c1"
    }
  ]
}