{
  "entity_a": {
    "slug": "claude-searchbot",
    "name": "Claude-SearchBot"
  },
  "entity_b": {
    "slug": "gptbot",
    "name": "GPTBot"
  },
  "fields_documented": 10,
  "claims": 17,
  "last_verified": "2026-09-13",
  "fields": [
    {
      "field": "cites_sources",
      "value_a": "not_documented",
      "value_b": null,
      "claim_id_a": 34,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "honours_crawl_delay",
      "value_a": "yes",
      "value_b": "not_documented",
      "claim_id_a": 29,
      "claim_id_b": 79,
      "same": false
    },
    {
      "field": "publishes_ip_list",
      "value_a": "yes",
      "value_b": "yes",
      "claim_id_a": 30,
      "claim_id_b": 80,
      "same": true
    },
    {
      "field": "purpose_documented",
      "value_a": "search",
      "value_b": "training",
      "claim_id_a": 32,
      "claim_id_b": 82,
      "same": false
    },
    {
      "field": "reads_llms_txt",
      "value_a": "not_documented",
      "value_b": null,
      "claim_id_a": 35,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "respects_robots_txt",
      "value_a": "yes",
      "value_b": "yes",
      "claim_id_a": 28,
      "claim_id_b": 78,
      "same": true
    },
    {
      "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": 33,
      "claim_id_b": 83,
      "same": true
    },
    {
      "field": "user_agent_string_full",
      "value_a": "not_documented",
      "value_b": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.4; +https://openai.com/gptbot",
      "claim_id_a": 36,
      "claim_id_b": 84,
      "same": false
    },
    {
      "field": "verifiable_by_rdns",
      "value_a": "not_documented",
      "value_b": "not_documented",
      "claim_id_a": 31,
      "claim_id_b": 81,
      "same": true
    }
  ],
  "differences": [
    {
      "field": "cites_sources",
      "statement_a": "Anthropic does not publish whether Claude search responses cite pages crawled by Claude-SearchBot.",
      "statement_b": null,
      "claim_id_a": 34,
      "claim_id_b": null
    },
    {
      "field": "honours_crawl_delay",
      "statement_a": "Claude-SearchBot respects the Crawl-delay directive in robots.txt when crawling domains.",
      "statement_b": "OpenAI does not publish whether GPTBot honours the robots.txt Crawl-delay directive.",
      "claim_id_a": 29,
      "claim_id_b": 79
    },
    {
      "field": "purpose_documented",
      "statement_a": "Claude-SearchBot analyses online content to improve the relevance and accuracy of Claude search responses.",
      "statement_b": "GPTBot crawls content that may be used to train OpenAI generative AI foundation models.",
      "claim_id_a": 32,
      "claim_id_b": 82
    },
    {
      "field": "reads_llms_txt",
      "statement_a": "Anthropic does not publish whether Claude-SearchBot reads llms.txt files.",
      "statement_b": null,
      "claim_id_a": 35,
      "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": "Anthropic does not publish a full user agent string for Claude-SearchBot.",
      "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": 36,
      "claim_id_b": 84
    }
  ],
  "sources": [
    "https://claude.com/crawling/bots.json",
    "https://developers.openai.com/api/docs/bots",
    "https://openai.com/gptbot.json",
    "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-content-from-the-web-and-how-can-site-owners-block-the-crawler"
  ]
}