# Bingbot vs GPTBot

Bingbot and GPTBot compared on 12 documented fields, from 19 claims, last verified 2026-09-14.

| Field | Bingbot | GPTBot | Comparison |
| --- | --- | --- | --- |
| cites_sources | yes | not documented | different |
| follows_noarchive | yes | not documented | different |
| honours_crawl_delay | yes | not_documented | different |
| opt_out_mechanism | yes | not documented | different |
| publishes_ip_list | yes | yes | same |
| purpose_documented | yes | training | different |
| reads_llms_txt | not_documented | not documented | different |
| respects_robots_txt | yes | yes | same |
| robots_txt_fetch_marker | not documented | yes | different |
| separate_search_and_training_tokens | no | yes | different |
| user_agent_string_full | Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm) | Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.4; +https://openai.com/gptbot | different |
| verifiable_by_rdns | yes | not_documented | different |

## Differences

| Field | Bingbot statement | GPTBot statement |
| --- | --- | --- |
| cites_sources | Copilot Search in Bing delivers clearly cited sources alongside generative answers to support publishers and content owners. | not documented |
| follows_noarchive | Bingbot excludes noarchive-tagged content from Copilot and Chat answers and from generative AI training data. | not documented |
| honours_crawl_delay | Microsoft states that a crawl-delay directive in robots.txt always takes precedence over Bing Webmaster Tools crawl control settings for Bingbot. | OpenAI does not publish whether GPTBot honours the robots.txt Crawl-delay directive. |
| opt_out_mechanism | Microsoft lets publishers block Bingbot content from Copilot answers and AI training using noarchive and nocache tags. | not documented |
| purpose_documented | Bingbot serves as Microsoft's standard crawler and handles most of Bing's daily web crawling. | GPTBot crawls content that may be used to train OpenAI generative AI foundation models. |
| reads_llms_txt | Microsoft does not publish whether Bingbot reads llms.txt files. | not documented |
| robots_txt_fetch_marker | not documented | OpenAI may add a robots.txt marker to the GPTBot user agent string when GPTBot fetches robots.txt files. |
| separate_search_and_training_tokens | Microsoft controls Bingbot's use in AI training through meta tags rather than publishing a separate training-specific crawler token. | OpenAI separates search and training controls into two robots.txt tokens: OAI-SearchBot for search and GPTBot for training. |
| user_agent_string_full | Bingbot sends a user agent string containing bingbot/2.0 and a link to Microsoft's bingbot.htm page. | GPTBot sends the user agent string Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.4; +https://openai.com/gptbot. |
| verifiable_by_rdns | Microsoft verifies Bingbot traffic through reverse DNS lookups that resolve to hostnames ending in search.msn.com. | OpenAI does not publish a reverse-DNS verification method for GPTBot. |

## Sources

- https://blogs.bing.com/search/April-2025/Introducing-Copilot-Search-in-Bing
- https://developers.openai.com/api/docs/bots
- https://openai.com/gptbot.json
- https://www.bing.com/toolbox/bingbot.json
- https://www.bing.com/webmasters/help/ai-performance-9f8e7d6c
- https://www.bing.com/webmasters/help/crawl-control-55a30303
- https://www.bing.com/webmasters/help/how-to-verify-bingbot-3905dc26
- https://www.bing.com/webmasters/help/robots-meta-tags-and-attributes-that-bing-supports-5198d240
- https://www.bing.com/webmasters/help/which-crawlers-does-bing-use-8c184ec0