{
 "name": "Kingy AI Accuracy Index: results",
 "updated": "November 10, 2026",
 "questions": 125,
 "private_questions": 39,
 "answers_per_model": 250,
 "models": [
  {
   "id": "openai/gpt-6.1-sol",
   "name": "GPT-6.1 Sol",
   "n": 250,
   "right": 148,
   "wrong": 3,
   "not_sure": 99,
   "none": 0,
   "range": [
    0.0,
    3.2
   ],
   "warned": 0,
   "stale": 3,
   "cost": 0.3688
  },
  {
   "id": "openai/gpt-6.1-terra",
   "name": "GPT-6.1 Terra",
   "n": 250,
   "right": 147,
   "wrong": 15,
   "not_sure": 88,
   "none": 0,
   "range": [
    2.4,
    9.6
   ],
   "warned": 0,
   "stale": 8,
   "cost": 0.4045
  },
  {
   "id": "openai/gpt-6-astra",
   "name": "GPT-6 Astra",
   "n": 250,
   "right": 146,
   "wrong": 2,
   "not_sure": 102,
   "none": 0,
   "range": [
    0.0,
    2.4
   ],
   "warned": 0,
   "stale": 2,
   "cost": 1.8576
  },
  {
   "id": "anthropic/claude-opus-5.5",
   "name": "Claude Opus 5.5",
   "n": 250,
   "right": 150,
   "wrong": 21,
   "not_sure": 79,
   "none": 0,
   "range": [
    4.0,
    13.2
   ],
   "warned": 19,
   "stale": 16,
   "cost": 1.9522
  },
  {
   "id": "anthropic/claude-sonnet-5.5",
   "name": "Claude Sonnet 5.5",
   "n": 250,
   "right": 155,
   "wrong": 26,
   "not_sure": 69,
   "none": 0,
   "range": [
    5.6,
    15.2
   ],
   "warned": 25,
   "stale": 18,
   "cost": 1.0275
  },
  {
   "id": "google/gemini-4-argon",
   "name": "Gemini 4 Argon",
   "n": 250,
   "right": 31,
   "wrong": 0,
   "not_sure": 219,
   "none": 0,
   "range": [
    0.0,
    0.0
   ],
   "warned": 0,
   "stale": 0,
   "cost": 0.2722
  },
  {
   "id": "google/gemini-3.8-flash",
   "name": "Gemini 3.8 Flash",
   "n": 250,
   "right": 56,
   "wrong": 27,
   "not_sure": 167,
   "none": 0,
   "range": [
    5.6,
    16.4
   ],
   "warned": 2,
   "stale": 12,
   "cost": 0.6684
  },
  {
   "id": "x-ai/grok-4.7",
   "name": "Grok 4.7",
   "n": 250,
   "right": 47,
   "wrong": 1,
   "not_sure": 195,
   "none": 7,
   "range": [
    0.0,
    1.2
   ],
   "warned": 0,
   "stale": 1,
   "cost": 1.8719
  },
  {
   "id": "qwen/qwen3.8-27b",
   "name": "Qwen 3.8 27B",
   "n": 250,
   "right": 54,
   "wrong": 49,
   "not_sure": 45,
   "none": 102,
   "range": [
    13.6,
    26.0
   ],
   "warned": 0,
   "stale": 13,
   "cost": 2.6277
  }
 ],
 "fields": {
  "none": "no readable answer (empty reply or no figure given)",
  "range": "95% range for the wrong share, by resampling questions",
  "warned": "wrong answers whose text told the reader to check (keyword count)",
  "stale": "wrong answers equal to a superseded official figure on record"
 }
}