{
  "schema": "chi-bench/submission/v1",
  "submission": {
    "id": "glm-5-2-openai-agents",
    "team": "Actava",
    "contact": "dark.savi@gmail.com",
    "agent": "openai-agents",
    "model": "z-ai/glm-5.2",
    "notes": "GLM-5.2 via the OpenAI Agents SDK harness, routed through OpenRouter.\n",
    "submitted_at": "2026-07-06T05:23:05Z"
  },
  "dataset": {
    "version": "chi-bench-v1.0.0",
    "domains": [
      "pa_provider",
      "pa_um",
      "cm"
    ],
    "name": "chi-bench"
  },
  "results": {
    "overall": {
      "n_trials": 75,
      "n_tasks": 75,
      "pass_at_1": 0.18666666666666668,
      "mean_cost_usd": 0.15959464888,
      "mean_walltime_s": 0.0
    },
    "per_domain": {
      "pa_provider": {
        "n_trials": 25,
        "n_tasks": 25,
        "pass_at_1": 0.2,
        "mean_cost_usd": 0.15565148484,
        "mean_walltime_s": 0.0
      },
      "pa_um": {
        "n_trials": 25,
        "n_tasks": 25,
        "pass_at_1": 0.32,
        "mean_cost_usd": 0.1808380908,
        "mean_walltime_s": 0.0
      },
      "cm": {
        "n_trials": 25,
        "n_tasks": 25,
        "pass_at_1": 0.04,
        "mean_cost_usd": 0.142294371,
        "mean_walltime_s": 0.0
      }
    },
    "mean_cost_usd": 0.15959464888,
    "mean_walltime_s": 0.0
  },
  "provenance": {
    "chi_bench_git_sha": "ee1e16d60afd8bc59a6d90a480fede19593ea84f",
    "image_digest": null,
    "judge_model": "claude-opus-4-7",
    "harness_version": "0.1.0",
    "code_dirty": true,
    "dataset_version": "chi-bench-v1.0.0",
    "environment": "modal",
    "started_at": "2026-07-02T04:22:04Z",
    "finished_at": "2026-07-02T04:48:05Z",
    "host": "Haolins-MacBook-Pro.local",
    "python_version": "3.12.12",
    "platform": "macOS-26.5.1-arm64-arm-64bit"
  }
}