{
 "benchmark": "Copywriting Arena",
 "round": 1,
 "updated": "2026-10-27",
 "status": "complete",
 "summary": "AI models write a short video ad script from the same brief. A fixed panel of AI judges compares the scripts in blind pairs, in both orders. A Bradley–Terry model turns the verdicts into ratings. The product is a real Indian car perfume; its brand name and trademarks are changed to a fictional brand, Noir Drive.",
 "methodology": "https://convictionlabs.ai/arena/methodology.md",
 "data": "https://convictionlabs.ai/arena/data.json",
 "judges": [
  "fable-5.1",
  "gpt-6.1-sol",
  "grok-4.7",
  "deepseek-v4-pro",
  "qwen3.8-max",
  "kimi-k3.1-pro",
  "glm-5.3-prime"
 ],
 "judgments": 1629,
 "order_consistency": 0.847,
 "invalid_judgments_excluded": 9,
 "definitions": {
  "rating": "Bradley-Terry strength on an Elo-like scale, 1000 = average model; ties count as one win each way.",
  "ci95": "2.5th-97.5th percentile over 200 bootstrap samples of script pairs.",
  "top5_chance": "share of 500 bootstrap samples of script pairs in which the model ranks in the top five.",
  "win_rate": "wins / judgments; tie = half a win; neither = a loss for both.",
  "gates_passed": "share of judge readings where the script passed all four gates.",
  "exact_length": "briefs where the spoken word count is inside the target range.",
  "cost_per_script_usd": "API list price; null for subscription calls."
 },
 "models": [
  {
   "model": "opus-5.5",
   "label": "Claude Opus 5.5",
   "lab": "Anthropic",
   "setting": "low reasoning",
   "role": "writer",
   "added_later": true,
   "rating": 1389,
   "ci95": [
    1327,
    1482
   ],
   "win_rate": 0.889,
   "gates_passed": 0.91,
   "exact_length": "3/3",
   "cost_per_script_usd": 0.0486,
   "seconds_per_script": 16,
   "judgments": 234,
   "top5_chance": 1.0,
   "rank": 1
  },
  {
   "model": "muse-wonder",
   "label": "Muse Wonder",
   "lab": "Meta",
   "setting": "low reasoning",
   "role": "writer",
   "added_later": true,
   "rating": 1177,
   "ci95": [
    1105,
    1260
   ],
   "win_rate": 0.678,
   "gates_passed": 0.927,
   "exact_length": "3/3",
   "cost_per_script_usd": 0.038,
   "seconds_per_script": 10,
   "judgments": 233,
   "top5_chance": 0.926,
   "rank": 2
  },
  {
   "model": "kimi-k3.1-pro",
   "label": "Kimi K3.1 Pro",
   "lab": "Moonshot AI",
   "setting": "low reasoning",
   "role": "writer and judge",
   "added_later": false,
   "rating": 1176,
   "ci95": [
    1121,
    1264
   ],
   "win_rate": 0.678,
   "gates_passed": 0.888,
   "exact_length": "3/3",
   "cost_per_script_usd": 0.0328,
   "seconds_per_script": 71,
   "judgments": 233,
   "top5_chance": 0.91,
   "rank": 3
  },
  {
   "model": "mimo-v2.6-pro",
   "label": "MiMo V2.6 Pro",
   "lab": "Xiaomi",
   "setting": "low reasoning",
   "role": "writer",
   "added_later": true,
   "rating": 1157,
   "ci95": [
    1075,
    1235
   ],
   "win_rate": 0.571,
   "gates_passed": 0.68,
   "exact_length": "1/3",
   "cost_per_script_usd": 0.003,
   "seconds_per_script": 41,
   "judgments": 231,
   "top5_chance": 0.79,
   "rank": 4
  },
  {
   "model": "grok-4.7",
   "label": "Grok 4.7",
   "lab": "xAI",
   "setting": "low reasoning",
   "role": "writer and judge",
   "added_later": false,
   "rating": 1153,
   "ci95": [
    1085,
    1227
   ],
   "win_rate": 0.658,
   "gates_passed": 0.957,
   "exact_length": "2/3",
   "cost_per_script_usd": 0.019,
   "seconds_per_script": 22,
   "judgments": 234,
   "top5_chance": 0.798,
   "rank": 5
  },
  {
   "model": "gpt-6-astra",
   "label": "GPT-6 Astra",
   "lab": "OpenAI",
   "setting": "low reasoning",
   "role": "writer",
   "added_later": true,
   "rating": 1125,
   "ci95": [
    1062,
    1202
   ],
   "win_rate": 0.645,
   "gates_passed": 0.996,
   "exact_length": "3/3",
   "cost_per_script_usd": null,
   "seconds_per_script": 31,
   "judgments": 234,
   "top5_chance": 0.476,
   "rank": 6
  },
  {
   "model": "deepseek-v4-pro",
   "label": "DeepSeek V4 Pro",
   "lab": "DeepSeek",
   "setting": "low reasoning",
   "role": "writer and judge",
   "added_later": false,
   "rating": 1067,
   "ci95": [
    999,
    1148
   ],
   "win_rate": 0.498,
   "gates_passed": 0.798,
   "exact_length": "3/3",
   "cost_per_script_usd": 0.0063,
   "seconds_per_script": 43,
   "judgments": 233,
   "top5_chance": 0.074,
   "rank": 7
  },
  {
   "model": "gpt-6.1-sol",
   "label": "GPT-6.1 Sol",
   "lab": "OpenAI",
   "setting": "low reasoning",
   "role": "writer and judge",
   "added_later": false,
   "rating": 1039,
   "ci95": [
    963,
    1114
   ],
   "win_rate": 0.541,
   "gates_passed": 0.983,
   "exact_length": "3/3",
   "cost_per_script_usd": null,
   "seconds_per_script": 22,
   "judgments": 233,
   "top5_chance": 0.018,
   "rank": 8
  },
  {
   "model": "gemini-4-argon",
   "label": "Gemini 4 Argon",
   "lab": "Google",
   "setting": "low reasoning",
   "role": "writer",
   "added_later": true,
   "rating": 975,
   "ci95": [
    856,
    1082
   ],
   "win_rate": 0.28,
   "gates_passed": 0.336,
   "exact_length": "0/3",
   "cost_per_script_usd": 0.0123,
   "seconds_per_script": 11,
   "judgments": 232,
   "top5_chance": 0.008,
   "rank": 9
  },
  {
   "model": "glm-5.3-prime",
   "label": "GLM-5.3 Prime",
   "lab": "Z.ai",
   "setting": "low reasoning",
   "role": "writer and judge",
   "added_later": false,
   "rating": 899,
   "ci95": [
    790,
    993
   ],
   "win_rate": 0.221,
   "gates_passed": 0.264,
   "exact_length": "1/3",
   "cost_per_script_usd": 0.0124,
   "seconds_per_script": 7,
   "judgments": 231,
   "top5_chance": 0.0,
   "rank": 10
  },
  {
   "model": "fable-5.1",
   "label": "Claude Fable 5.1",
   "lab": "Anthropic",
   "setting": "low reasoning",
   "role": "writer and judge",
   "added_later": false,
   "rating": 799,
   "ci95": [
    706,
    884
   ],
   "win_rate": 0.125,
   "gates_passed": 0.151,
   "exact_length": "0/3",
   "cost_per_script_usd": 0.0925,
   "seconds_per_script": 14,
   "judgments": 232,
   "top5_chance": 0.0,
   "rank": 11
  },
  {
   "model": "qwen3.8-max",
   "label": "Qwen 3.8 Max",
   "lab": "Alibaba",
   "setting": "low reasoning",
   "role": "writer and judge",
   "added_later": false,
   "rating": 741,
   "ci95": [
    646,
    815
   ],
   "win_rate": 0.085,
   "gates_passed": 0.124,
   "exact_length": "1/3",
   "cost_per_script_usd": 0.0472,
   "seconds_per_script": 31,
   "judgments": 234,
   "top5_chance": 0.0,
   "rank": 12
  },
  {
   "model": "llama-3.1-70b",
   "label": "Llama 3.1 70B",
   "lab": "Meta, 2024",
   "setting": "no reasoning",
   "role": "anchor",
   "added_later": false,
   "rating": 675,
   "ci95": [
    560,
    762
   ],
   "win_rate": 0.073,
   "gates_passed": 0.253,
   "exact_length": "1/3",
   "cost_per_script_usd": 0.0019,
   "seconds_per_script": 9,
   "judgments": 233,
   "top5_chance": 0.0,
   "rank": 13
  },
  {
   "model": "mistral-small-3",
   "label": "Mistral Small 3",
   "lab": "Mistral, early 2025",
   "setting": "no reasoning",
   "role": "anchor",
   "added_later": false,
   "rating": 628,
   "ci95": [
    494,
    722
   ],
   "win_rate": 0.048,
   "gates_passed": 0.1,
   "exact_length": "3/3",
   "cost_per_script_usd": 0.0002,
   "seconds_per_script": 13,
   "judgments": 231,
   "top5_chance": 0.0,
   "rank": 14
  }
 ]
}