{
 "effort": null,
 "ended": "2026-09-23T16:22:12Z",
 "label": "claude-sonnet-5",
 "model": "claude-sonnet-5",
 "n_expected": 108,
 "pass": 1,
 "served_by_other": 0,
 "started": "2026-09-23T16:18:33Z",
 "stopped": null,
 "summary": {
  "accuracy": 0.9444444444444444,
  "brier": 0.1111111111111111,
  "correct": 102,
  "errors": 0,
  "eval_tokens_total": 7705,
  "floored_rows": 0,
  "letters_floored_total": 0,
  "median_seconds": 1.6498024120046466,
  "n": 108,
  "n_labelled": 108,
  "n_reached": 108,
  "p95_seconds": 3.744105074998515,
  "prompt_tokens_total": 101929,
  "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": 0.9444444444444444,
    "correct": 102,
    "gap": 0.05555555555555558,
    "hi": 1.0,
    "lo": 0.9,
    "mean_p": 1.0,
    "n": 108,
    "sum_p": 108.0
   }
  ],
  "unparsed": 0
 },
 "task": "c"
}