{
  "schema": "chi-bench/submission/v1",
  "submission": {
    "id": "chi-bench-leaderboard-2026-05-15-openai-agents-moonshotai-kimi-k2-6",
    "team": "chi-Bench Leaderboard",
    "contact": "leaderboard@actava.ai",
    "agent": "openai-agents",
    "model": "moonshotai/kimi-k2.6",
    "notes": "Paper-baseline submission generated from the curated25 full-matrix experiment logs. Trials are the latest available run per (domain, task).\n",
    "submitted_at": "2026-05-04T07:47:06Z"
  },
  "dataset": {
    "version": "chi-bench-v1.0.0",
    "domains": [
      "pa_provider",
      "pa_um",
      "cm"
    ],
    "name": "chi-bench"
  },
  "results": {
    "overall": {
      "n_trials": 225,
      "n_tasks": 75,
      "pass_at_1": 0.15111111111111108,
      "mean_cost_usd": 1.2181144675555555,
      "mean_walltime_s": 1422.9322827777778
    },
    "per_domain": {
      "pa_provider": {
        "n_trials": 75,
        "n_tasks": 25,
        "pass_at_1": 0.1733333333333333,
        "mean_cost_usd": 1.4488802114666666,
        "mean_walltime_s": 1210.6539233066667
      },
      "pa_um": {
        "n_trials": 75,
        "n_tasks": 25,
        "pass_at_1": 0.2533333333333333,
        "mean_cost_usd": 1.1204133075466667,
        "mean_walltime_s": 1351.8375677733334
      },
      "cm": {
        "n_trials": 75,
        "n_tasks": 25,
        "pass_at_1": 0.026666666666666665,
        "mean_cost_usd": 1.0850498836533333,
        "mean_walltime_s": 1706.3053572533333
      }
    },
    "mean_cost_usd": 1.2181144675555555,
    "mean_walltime_s": 1422.9322827777778
  },
  "provenance": {
    "chi_bench_git_sha": "a077ad96e11b813b20e0adf7065ebd52e524159d",
    "image_digest": null,
    "judge_model": "claude-opus-4-7",
    "harness_version": "0.1.0",
    "code_dirty": false,
    "dataset_version": "chi-bench-v1.0.0",
    "environment": "modal",
    "started_at": "2026-05-03T09:00:39Z",
    "finished_at": "2026-05-04T07:47:06Z",
    "host": "modal",
    "python_version": "3.12.3",
    "platform": "linux"
  }
}