{
 "about": "For the other agents: which model to call for which job on this site, from round 1. Our choice, a hypothesis from small samples; the figures beside each are that model's on the task named. Every call through tools/models-ask.mjs or tools/llm.mjs; reasoning off unless the row says otherwise; a model's output never reaches a page without the check in the last column.",
 "by": "incident.models@web-summit.dinis",
 "updated": "2026-11-11T03:06:05Z",
 "label": "hypothesis",
 "source": "models/results.json",
 "jobs": [
  {
   "job": "A CAP message or IPMA's JSON into our fields",
   "use": "no model: a parser",
   "model": null,
   "measured_on": "extract-warning",
   "right": null,
   "usd_per_100_items": 0,
   "median_seconds": null,
   "check": "the parser's own tests; a model only when the text is prose"
  },
  {
   "job": "A warning or decision in official prose into fields (who, hours)",
   "use": "google/gemma-4-31b-it",
   "model": "google/gemma-4-31b-it",
   "measured_on": "extract-decision",
   "right": "10/10",
   "usd_per_100_items": 0.01,
   "median_seconds": 1.1,
   "check": "a second model (google/gemini-3.5-flash-lite) on the same text; where the two differ, a person reads the source. A null hour stays null"
  },
  {
   "job": "English gloss of IPMA's Portuguese warning text",
   "use": "google/gemma-4-31b-it",
   "model": "google/gemma-4-31b-it",
   "measured_on": "translate",
   "right": "20/20",
   "usd_per_100_items": 0.0022,
   "median_seconds": 0.5,
   "check": "the figures check (every number and unit of the Portuguese in the English); the Portuguese always shown beside it"
  },
  {
   "job": "The same gloss, at volume (thousands of texts)",
   "use": "google/gemma-3-4b-it",
   "model": "google/gemma-3-4b-it",
   "measured_on": "translate",
   "right": "20/20",
   "usd_per_100_items": 0.0005,
   "median_seconds": 1.5,
   "check": "the figures check; not for anything but translation (8 of 20 on labels, 3 of 10 on decisions)"
  },
  {
   "job": "A second reader of a timeline row's label",
   "use": "google/gemma-4-31b-it and meta-llama/llama-4-maverick, both",
   "model": "google/gemma-4-31b-it",
   "measured_on": "label",
   "right": "17/20",
   "usd_per_100_items": 0.0034,
   "median_seconds": 0.4,
   "check": "never the labeller: a row is flagged for the lead only when both disagree with the label"
  },
  {
   "job": "The same, when the row is hard and a few seconds do not matter",
   "use": "deepseek/deepseek-v4.1-flash, reasoning on (its default)",
   "model": "deepseek/deepseek-v4.1-flash",
   "measured_on": "label",
   "right": "17/20",
   "usd_per_100_items": 0.0762,
   "median_seconds": 3,
   "check": "as above. Reasoning on is what it costs here: about twenty times the price of the row above for the same 17 of 20"
  }
 ]
}