{
 "arm": {
  "mode": "generate",
  "model": "gpt-4o-2024-11-20",
  "name": "openai:gpt-4o-2024-11-20",
  "note": "effort=n/a (no reasoning) temperature=0 max_tokens=8 api=chat",
  "runtime": "openai",
  "seed": 20260921
 },
 "ended": "2026-09-23T17:14:12Z",
 "instrument": {
  "doorman_planted_sha256": "4daf059c26a47a84fa3b73630a64ba1a348da72c2e5df7f3c28c007b67da22f7",
  "instructions": {
   "c": "Six people are at a dinner table. Which of them said the line below?\nLine: %s",
   "d": "DOORMAN_SYSTEM v1.2 (kit)"
  },
  "jev_run_addenda_py_sha256": "a34aca61833ed0c5860c91c7e2e227429e8ea9e2e50fec68d7b7fec15d89acab",
  "jev_run_py_sha256": "withheld-2026-10-14",
  "oai_py_sha256": "b1efebe365581c174f8b304b1791a773a6ffaf933b0be00454543f45be10e60a",
  "run_openai_py_sha256": "fcd38a428668fefd84f1f7d07677c4af25f84f5d10146d3be93848058a309755",
  "task_c_sha256": "61a0b1d6e7cf66fd91992c0c3a4572f6fbae90e6471048fd7dc1eb41ff2d7f39"
 },
 "limit": 0,
 "model": "gpt-4o-2024-11-20",
 "price": {
  "basis": "alias row (dated suffix stripped)",
  "cache_write": null,
  "cached_input": 1.25,
  "input": 2.5,
  "model": "gpt-4o-2024-11-20",
  "output": 10.0,
  "row": "gpt-4o"
 },
 "pricing_read_at": "2026-09-23T15:40:55Z",
 "pricing_source": "https://developers.openai.com/api/docs/pricing.md",
 "profile": {
  "api": "chat",
  "max_out": 8,
  "reasoning": false,
  "reasoning_effort": null,
  "seed": 20260921,
  "stream": true,
  "temperature": 0,
  "token_param": "max_tokens"
 },
 "stage": "rows",
 "started": "2026-09-23T17:10:27Z",
 "stopped": null,
 "summary": {
  "accuracy": 0.8240740740740741,
  "brier": 0.35185185185185186,
  "content_filter": 0,
  "correct": 89,
  "errors": 0,
  "eval_tokens_total": 251,
  "failed_calls": 0,
  "floored_rows": 0,
  "format_failures": 0,
  "latency_s_median": 1.0792044929912663,
  "latency_s_n": 108,
  "latency_s_p95": 6.694935514999088,
  "length_finishes_in_rate": 0,
  "letter_only_replies": 91,
  "letters_floored_total": 0,
  "median_seconds": 1.0792044929912663,
  "n": 108,
  "n_labelled": 108,
  "n_reached": 108,
  "out_tok_per_s_median": 36.21778008147574,
  "out_tok_per_s_n": 108,
  "out_tok_per_s_p95": 80.02740458254627,
  "p95_seconds": 6.694935514999088,
  "prefill_tok_per_s": "not given: the API returns no server prefill timing",
  "prompt_tokens_total": 29701,
  "reasoning_tokens_max": 0,
  "refusal_field": 0,
  "refused": 0,
  "refused_by_reason": {},
  "reliability": [
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.1,
    "lo": 0.0,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.2,
    "lo": 0.1,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.3,
    "lo": 0.2,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.4,
    "lo": 0.3,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.5,
    "lo": 0.4,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.6,
    "lo": 0.5,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.7,
    "lo": 0.6,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.8,
    "lo": 0.7,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": null,
    "correct": 0,
    "gap": null,
    "hi": 0.9,
    "lo": 0.8,
    "mean_p": null,
    "n": 0,
    "sum_p": 0.0
   },
   {
    "accuracy": 0.8240740740740741,
    "correct": 89,
    "gap": 0.17592592592592593,
    "hi": 1.0,
    "lo": 0.9,
    "mean_p": 1.0,
    "n": 108,
    "sum_p": 108.0
   }
  ],
  "resolved_models": [
   "gpt-4o-2024-11-20"
  ],
  "strict_accuracy": 0.8240740740740741,
  "strict_correct": 89,
  "strict_wilson95": [
   0.7415045937948218,
   0.8843813767398171
  ],
  "system_fingerprints": [
   "fp_3500860c9d",
   "fp_54f5955b43",
   "fp_59530732f1",
   "fp_a187b25b83",
   "fp_c6126d64e4",
   "fp_e8c37e2ed8"
  ],
  "timing_mode": [
   "streamed, network-included"
  ],
  "tokens_cached": 0,
  "tokens_in": 29701,
  "tokens_out": 251,
  "tokens_reasoning": 0,
  "tokens_visible": 251,
  "truncated": 0,
  "ttfb_s_median": 1.008748458501941,
  "ttfb_s_n": 108,
  "ttfb_s_p95": 6.6356815960025415,
  "ttft_s_median": 1.0265128609971725,
  "ttft_s_n": 108,
  "ttft_s_p95": 6.653658783005085,
  "unparsed": 0,
  "usd": 0.0767625,
  "usd_per_correct": 0.0008625,
  "usd_per_item": 0.0007107638888888888,
  "wilson95": [
   0.7415045937948218,
   0.8843813767398171
  ]
 },
 "task": "c",
 "variant": null,
 "variant_id": "gpt-4o-2024-11-20",
 "wall_seconds": 225.14871252400917
}