{
  "transport": "Codex CLI / existing login",
  "platform_api_tested": false,
  "prompt_sha256": "786fe7c00cdfe85eabe70e47c4f47c8e332b20e5dfea82a012560170f6fe0ad1",
  "schema_sha256": "ccd9d4a6c9be7a8a0e624c244db25c10a9346afdb8c37a256d98b13f65ea2704",
  "effort": "low",
  "repeats": 2,
  "cli_version": "codex-cli 0.160.0",
  "runs": [
    {
      "model_requested": "gpt-6-sol",
      "mode": "plain",
      "repeat": 1,
      "started_utc": "2026-10-05T02:08:43.148367+00:00",
      "elapsed_seconds": 35.355,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 16941,
        "cached_input_tokens": 12032,
        "cache_write_input_tokens": 0,
        "output_tokens": 1270,
        "reasoning_output_tokens": 33
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-1-plain-01",
      "backend_snapshot": "not exposed by CLI events"
    },
    {
      "model_requested": "gpt-6-luna",
      "mode": "plain",
      "repeat": 1,
      "started_utc": "2026-10-05T02:09:18.512875+00:00",
      "elapsed_seconds": 32.965,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 16762,
        "cached_input_tokens": 11008,
        "cache_write_input_tokens": 0,
        "output_tokens": 1251,
        "reasoning_output_tokens": 0
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-2-plain-01",
      "backend_snapshot": "not exposed by CLI events"
    },
    {
      "model_requested": "gpt-6-sol",
      "mode": "schema",
      "repeat": 1,
      "started_utc": "2026-10-05T02:09:51.484694+00:00",
      "elapsed_seconds": 22.385,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 17087,
        "cached_input_tokens": 0,
        "cache_write_input_tokens": 0,
        "output_tokens": 931,
        "reasoning_output_tokens": 58
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-1-schema-01",
      "backend_snapshot": "not exposed by CLI events"
    },
    {
      "model_requested": "gpt-6-luna",
      "mode": "schema",
      "repeat": 1,
      "started_utc": "2026-10-05T02:10:13.880338+00:00",
      "elapsed_seconds": 22.507,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 16908,
        "cached_input_tokens": 0,
        "cache_write_input_tokens": 0,
        "output_tokens": 829,
        "reasoning_output_tokens": 0
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-2-schema-01",
      "backend_snapshot": "not exposed by CLI events"
    },
    {
      "model_requested": "gpt-6-sol",
      "mode": "plain",
      "repeat": 2,
      "started_utc": "2026-10-05T02:10:36.392775+00:00",
      "elapsed_seconds": 34.007,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 16941,
        "cached_input_tokens": 12032,
        "cache_write_input_tokens": 0,
        "output_tokens": 1267,
        "reasoning_output_tokens": 49
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-1-plain-02",
      "backend_snapshot": "not exposed by CLI events"
    },
    {
      "model_requested": "gpt-6-luna",
      "mode": "plain",
      "repeat": 2,
      "started_utc": "2026-10-05T02:11:10.406430+00:00",
      "elapsed_seconds": 20.725,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 16762,
        "cached_input_tokens": 11008,
        "cache_write_input_tokens": 0,
        "output_tokens": 825,
        "reasoning_output_tokens": 0
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-2-plain-02",
      "backend_snapshot": "not exposed by CLI events"
    },
    {
      "model_requested": "gpt-6-sol",
      "mode": "schema",
      "repeat": 2,
      "started_utc": "2026-10-05T02:11:31.141761+00:00",
      "elapsed_seconds": 24.989,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 17087,
        "cached_input_tokens": 0,
        "cache_write_input_tokens": 0,
        "output_tokens": 933,
        "reasoning_output_tokens": 51
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-1-schema-02",
      "backend_snapshot": "not exposed by CLI events"
    },
    {
      "model_requested": "gpt-6-luna",
      "mode": "schema",
      "repeat": 2,
      "started_utc": "2026-10-05T02:11:56.138018+00:00",
      "elapsed_seconds": 21.664,
      "exit_code": 0,
      "tool_items": [],
      "usage": {
        "input_tokens": 16908,
        "cached_input_tokens": 0,
        "cache_write_input_tokens": 0,
        "output_tokens": 847,
        "reasoning_output_tokens": 0
      },
      "grade": {
        "json_parse": true,
        "contract_pass": true,
        "contract_error": null,
        "fact_matches": 12,
        "reference_coverage": 12,
        "total_records": 12,
        "record_errors": []
      },
      "directory": "model-2-schema-02",
      "backend_snapshot": "not exposed by CLI events"
    }
  ]
}
