{
  "schema": "chi-bench/submission/v1",
  "submission": {
    "id": "gpt-5-6-sol-codex",
    "team": "Actava",
    "contact": "dark.savi@gmail.com",
    "agent": "codex",
    "model": "openai/gpt-5.6-sol",
    "notes": "GPT-5.6 Sol via the stock Codex harness with MCP tools.\nCodex CLI 0.145.0; high reasoning effort and automatic reasoning summaries.\n",
    "submitted_at": "2026-07-24T23:01:25Z"
  },
  "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": 0.25333333333333335,
      "mean_cost_usd": 2.060206873333333,
      "mean_walltime_s": 239.12849446666664
    },
    "per_domain": {
      "pa_provider": {
        "n_trials": 25,
        "n_tasks": 25,
        "pass_at_1": 0.36,
        "mean_cost_usd": 1.3676000799999999,
        "mean_walltime_s": 126.57268260000001
      },
      "pa_um": {
        "n_trials": 25,
        "n_tasks": 25,
        "pass_at_1": 0.28,
        "mean_cost_usd": 1.8998682,
        "mean_walltime_s": 198.10586116
      },
      "cm": {
        "n_trials": 25,
        "n_tasks": 25,
        "pass_at_1": 0.12,
        "mean_cost_usd": 2.91315234,
        "mean_walltime_s": 392.70693964
      }
    },
    "mean_cost_usd": 2.060206873333333,
    "mean_walltime_s": 239.12849446666664
  },
  "provenance": {
    "chi_bench_git_sha": "5af8d107b2d7ba56231bc4168d6bc7cb5fbb0ceb",
    "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": "2026-07-22T02:41:32.718905Z",
    "finished_at": "2026-07-22T04:52:39.419746Z",
    "source": "frontier_models_full_2026_07 experiment matrix",
    "matrix_config": "configs/experiments/frontier_models_full_2026_07.yaml"
  }
}