{ "entity_a": { "slug": "claudebot", "name": "ClaudeBot" }, "entity_b": { "slug": "perplexitybot", "name": "PerplexityBot" }, "fields_documented": 14, "claims": 21, "last_verified": "2026-09-15", "fields": [ { "field": "anti_circumvention_stance", "value_a": "documented", "value_b": null, "claim_id_a": 53, "claim_id_b": null, "same": false }, { "field": "cites_sources", "value_a": null, "value_b": "yes", "claim_id_a": null, "claim_id_b": 118, "same": false }, { "field": "honours_crawl_delay", "value_a": "yes", "value_b": "not_documented", "claim_id_a": 48, "claim_id_b": 113, "same": false }, { "field": "observed_fetches_json", "value_a": "yes", "value_b": null, "claim_id_a": 143, "claim_id_b": null, "same": false }, { "field": "observed_fetches_markdown", "value_a": "yes", "value_b": null, "claim_id_a": 142, "claim_id_b": null, "same": false }, { "field": "observed_first_request_path", "value_a": "/sitemap.xml", "value_b": null, "claim_id_a": 144, "claim_id_b": null, "same": false }, { "field": "observed_format_pass_order", "value_a": "html_json_md", "value_b": null, "claim_id_a": 145, "claim_id_b": null, "same": false }, { "field": "publishes_ip_list", "value_a": "yes", "value_b": "yes", "claim_id_a": 49, "claim_id_b": 114, "same": true }, { "field": "purpose_documented", "value_a": "training", "value_b": "search", "claim_id_a": 51, "claim_id_b": 116, "same": false }, { "field": "reads_llms_txt", "value_a": null, "value_b": "not_documented", "claim_id_a": null, "claim_id_b": 119, "same": false }, { "field": "respects_robots_txt", "value_a": "yes", "value_b": "yes", "claim_id_a": 47, "claim_id_b": 112, "same": true }, { "field": "separate_search_and_training_tokens", "value_a": "yes", "value_b": "not_documented", "claim_id_a": 52, "claim_id_b": 117, "same": false }, { "field": "user_agent_string_full", "value_a": "not_documented", "value_b": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot)", "claim_id_a": 54, "claim_id_b": 120, "same": false }, { "field": "verifiable_by_rdns", "value_a": "not_documented", "value_b": "not_documented", "claim_id_a": 50, "claim_id_b": 115, "same": true } ], "differences": [ { "field": "anti_circumvention_stance", "statement_a": "ClaudeBot respects anti-circumvention technologies and does not bypass CAPTCHAs on crawled sites.", "statement_b": null, "claim_id_a": 53, "claim_id_b": null }, { "field": "cites_sources", "statement_a": null, "statement_b": "Perplexity links to the websites that PerplexityBot surfaces in Perplexity search results.", "claim_id_a": null, "claim_id_b": 118 }, { "field": "honours_crawl_delay", "statement_a": "Anthropic supports the non-standard robots.txt Crawl-delay extension for ClaudeBot.", "statement_b": "Perplexity does not publish whether PerplexityBot honours the robots.txt Crawl-delay directive.", "claim_id_a": 48, "claim_id_b": 113 }, { "field": "observed_fetches_json", "statement_a": "ClaudeBot made 177 JSON requests to Rattlesnakes By Mail between 2026-09-13T20:00Z and 2026-09-15T09:00Z, covering the .json twin of 170 base paths. The .json URLs of Rattlesnakes By Mail appear in no entry of the 171 URL sitemap.", "statement_b": null, "claim_id_a": 143, "claim_id_b": null }, { "field": "observed_fetches_markdown", "statement_a": "ClaudeBot fetched the .md twin of 170 base paths on Rattlesnakes By Mail between 2026-09-13T20:00Z and 2026-09-15T09:00Z, 170 Markdown requests of 542 ClaudeBot requests in that window. The .md URLs of Rattlesnakes By Mail appear in no entry of the 171 URL sitemap.", "statement_b": null, "claim_id_a": 142, "claim_id_b": null }, { "field": "observed_first_request_path", "statement_a": "ClaudeBot's first request to Rattlesnakes By Mail between 2026-09-13T20:00Z and 2026-09-15T09:00Z was /sitemap.xml at 2026-09-14T19:53:45Z. ClaudeBot fetched /robots.txt on the second request to Rattlesnakes By Mail.", "statement_b": null, "claim_id_a": 144, "claim_id_b": null }, { "field": "observed_format_pass_order", "statement_a": "ClaudeBot fetched Rattlesnakes By Mail in three format passes between 2026-09-13T20:00Z and 2026-09-15T09:00Z, HTML from 2026-09-14T20:52Z to 2026-09-14T20:57Z, then JSON from 2026-09-14T21:37Z to 2026-09-14T21:56Z, then Markdown from 2026-09-14T21:37Z to 2026-09-14T21:57Z. The same order holds on 170 of 170 base paths that ClaudeBot fetched in all three formats on Rattlesnakes By Mail.", "statement_b": null, "claim_id_a": 145, "claim_id_b": null }, { "field": "purpose_documented", "statement_a": "ClaudeBot collects web content for training Anthropic generative AI models.", "statement_b": "PerplexityBot surfaces and links websites in Perplexity search results.", "claim_id_a": 51, "claim_id_b": 116 }, { "field": "reads_llms_txt", "statement_a": null, "statement_b": "Perplexity does not publish whether PerplexityBot reads llms.txt files.", "claim_id_a": null, "claim_id_b": 119 }, { "field": "separate_search_and_training_tokens", "statement_a": "Anthropic separates training and search controls into two robots.txt tokens: ClaudeBot for training and Claude-SearchBot for search.", "statement_b": "Perplexity does not document a separate training crawler token alongside PerplexityBot.", "claim_id_a": 52, "claim_id_b": 117 }, { "field": "user_agent_string_full", "statement_a": "Anthropic does not publish a full user agent string for ClaudeBot.", "statement_b": "PerplexityBot sends the user agent string Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot).", "claim_id_a": 54, "claim_id_b": 120 } ], "sources": [ "https://claude.com/crawling/bots.json", "https://docs.perplexity.ai/docs/resources/perplexity-crawlers", "https://rattlesnakesbymail.com/observed/claudebot", "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-content-from-the-web-and-how-can-site-owners-block-the-crawler", "https://www.perplexity.ai/perplexitybot.json" ] }