{
  "entity_a": {
    "slug": "google-extended",
    "name": "Google-Extended"
  },
  "entity_b": {
    "slug": "gptbot",
    "name": "GPTBot"
  },
  "fields_documented": 10,
  "claims": 16,
  "last_verified": "2026-09-13",
  "fields": [
    {
      "field": "honours_crawl_delay",
      "value_a": "n/a",
      "value_b": "not_documented",
      "claim_id_a": 56,
      "claim_id_b": 79,
      "same": false
    },
    {
      "field": "publishes_ip_list",
      "value_a": "no",
      "value_b": "yes",
      "claim_id_a": 57,
      "claim_id_b": 80,
      "same": false
    },
    {
      "field": "purpose_documented",
      "value_a": "policy_only",
      "value_b": "training",
      "claim_id_a": 59,
      "claim_id_b": 82,
      "same": false
    },
    {
      "field": "respects_robots_txt",
      "value_a": "n/a",
      "value_b": "yes",
      "claim_id_a": 55,
      "claim_id_b": 78,
      "same": false
    },
    {
      "field": "robots_token_differs_from_ua",
      "value_a": "yes",
      "value_b": null,
      "claim_id_a": 62,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "robots_txt_fetch_marker",
      "value_a": null,
      "value_b": "yes",
      "claim_id_a": null,
      "claim_id_b": 85,
      "same": false
    },
    {
      "field": "separate_search_and_training_tokens",
      "value_a": "yes",
      "value_b": "yes",
      "claim_id_a": 60,
      "claim_id_b": 83,
      "same": true
    },
    {
      "field": "user_agent_string_full",
      "value_a": null,
      "value_b": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.4; +https://openai.com/gptbot",
      "claim_id_a": null,
      "claim_id_b": 84,
      "same": false
    },
    {
      "field": "verifiable_by_rdns",
      "value_a": "n/a",
      "value_b": "not_documented",
      "claim_id_a": 58,
      "claim_id_b": 81,
      "same": false
    },
    {
      "field": "what_it_controls",
      "value_a": "Gemini model training and grounding, not Search inclusion",
      "value_b": null,
      "claim_id_a": 61,
      "claim_id_b": null,
      "same": false
    }
  ],
  "differences": [
    {
      "field": "honours_crawl_delay",
      "statement_a": "Google does not publish any Crawl-delay behaviour for the Google-Extended token.",
      "statement_b": "OpenAI does not publish whether GPTBot honours the robots.txt Crawl-delay directive.",
      "claim_id_a": 56,
      "claim_id_b": 79
    },
    {
      "field": "publishes_ip_list",
      "statement_a": "Google publishes no IP list for Google-Extended because Google-Extended has no separate HTTP request user agent string.",
      "statement_b": "OpenAI publishes the IP address ranges used by GPTBot as a JSON file at https://openai.com/gptbot.json.",
      "claim_id_a": 57,
      "claim_id_b": 80
    },
    {
      "field": "purpose_documented",
      "statement_a": "Google-Extended is a standalone product token that controls whether Google uses crawled content to train Gemini models.",
      "statement_b": "GPTBot crawls content that may be used to train OpenAI generative AI foundation models.",
      "claim_id_a": 59,
      "claim_id_b": 82
    },
    {
      "field": "respects_robots_txt",
      "statement_a": "Google-Extended is a robots.txt token that publishers set to control use of crawled content for Gemini training.",
      "statement_b": "GPTBot honours robots.txt rules that webmasters set for the GPTBot token.",
      "claim_id_a": 55,
      "claim_id_b": 78
    },
    {
      "field": "robots_token_differs_from_ua",
      "statement_a": "Google-Extended is a robots.txt control token and does not correspond to a crawler user agent string.",
      "statement_b": null,
      "claim_id_a": 62,
      "claim_id_b": null
    },
    {
      "field": "robots_txt_fetch_marker",
      "statement_a": null,
      "statement_b": "OpenAI may add a robots.txt marker to the GPTBot user agent string when GPTBot fetches robots.txt files.",
      "claim_id_a": null,
      "claim_id_b": 85
    },
    {
      "field": "user_agent_string_full",
      "statement_a": null,
      "statement_b": "GPTBot sends the user agent string Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.4; +https://openai.com/gptbot.",
      "claim_id_a": null,
      "claim_id_b": 84
    },
    {
      "field": "verifiable_by_rdns",
      "statement_a": "Google does not publish a reverse-DNS verification method for Google-Extended.",
      "statement_b": "OpenAI does not publish a reverse-DNS verification method for GPTBot.",
      "claim_id_a": 58,
      "claim_id_b": 81
    },
    {
      "field": "what_it_controls",
      "statement_a": "Google-Extended controls AI training and grounding in Google systems and does not control Google Search inclusion.",
      "statement_b": null,
      "claim_id_a": 61,
      "claim_id_b": null
    }
  ],
  "sources": [
    "https://developers.google.com/search/docs/appearance/ai-features",
    "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
    "https://developers.openai.com/api/docs/bots",
    "https://openai.com/gptbot.json"
  ]
}