Google AI Mode · AI Infrastructure · Machine Relations Index
Which sources does Google AI Mode cite most among AI Infrastructure sources?
As of October 25, 2026, among sources with a published AI Infrastructure segment, LinkedIn is the most-cited source in Google AI Mode answers across the whole window, cited in 24.59% of 1,895 observed Google AI Mode runs.
A rate is the source's share of Google AI Mode's observed runs across the whole window, not a rate inside AI Infrastructure. The public release does not record a separate rate for one engine inside one category. Sources are listed only when they have a published segment here, which means that segment cleared the evidence floor.
Ranking
Sources ranked by citation rate
| Rank | Source | Source role | Citation rate | Cited runs | Engine's observed runs | Confidence |
|---|---|---|---|---|---|---|
| #1 of 501 | Community and social platform | 24.59% | 466 | 1,895 | A | |
| #2 of 501 | Community and social platform | 17.15% | 325 | 1,895 | A | |
| #3 of 501 | YouTube | Search or media platform | 12.98% | 246 | 1,895 | A |
| #4 of 501 | Medium | Community and social platform | 10.66% | 202 | 1,895 | A |
| #5 of 501 | Yahoo News | Editorial publication | 6.70% | 127 | 1,895 | A |
| #6 of 501 | Forbes | Editorial publication | 5.80% | 110 | 1,895 | A |
| #7 of 501 | G2 | Market and company database | 4.54% | 86 | 1,895 | A |
| #8 of 501 | Substack.com | Community and social platform | 3.91% | 74 | 1,895 | A |
| #9 of 501 | NIH | Academic and government source | 3.38% | 64 | 1,895 | A |
| #10 of 501 | Facebook.com | Community and social platform | 3.01% | 57 | 1,895 | B |
| #10 of 501 | Microsoft.com | Vendor-owned source | 3.01% | 57 | 1,895 | A |
| #12 of 501 | Instagram.com | Other observed source | 2.90% | 55 | 1,895 | B |
| #13 of 501 | Ibm.com | Vendor-owned source | 2.59% | 49 | 1,895 | A |
| #14 of 501 | Sciencedirect.com | Academic and government source | 2.27% | 43 | 1,895 | B |
| #15 of 501 | Mordorintelligence.com | Market and company database | 2.01% | 38 | 1,895 | B |
| #16 of 501 | Marketsandmarkets.com | Market and company database | 1.95% | 37 | 1,895 | B |
| #17 of 501 | TechTarget | Editorial publication | 1.90% | 36 | 1,895 | A |
| #18 of 501 | Salesforce.com | Vendor-owned source | 1.79% | 34 | 1,895 | B |
| #19 of 501 | Amazon.com | Other observed source | 1.69% | 32 | 1,895 | A |
| #19 of 501 | Tech Insider | Editorial publication | 1.69% | 32 | 1,895 | B |
| #21 of 501 | Y Combinator | Community and social platform | 1.53% | 29 | 1,895 | B |
| #22 of 501 | Mckinsey.com | Analyst and consulting research | 1.42% | 27 | 1,895 | C |
| #22 of 501 | Researchgate.net | Academic and government source | 1.42% | 27 | 1,895 | B |
| #24 of 501 | Dev.to | Community and social platform | 1.32% | 25 | 1,895 | A |
| #25 of 501 | CIO | Editorial publication | 1.21% | 23 | 1,895 | C |
| #25 of 501 | Redhat.com | Vendor-owned source | 1.21% | 23 | 1,895 | B |
| #25 of 501 | Thomsonreuters.com | Market and company database | 1.21% | 23 | 1,895 | C |
| #28 of 501 | Arxiv.org | Academic and government source | 1.16% | 22 | 1,895 | A |
| #28 of 501 | Databricks.com | Vendor-owned source | 1.16% | 22 | 1,895 | B |
| #28 of 501 | Intuitionlabs.ai | Vendor-owned source | 1.16% | 22 | 1,895 | C |
| #31 of 501 | Devopsschool.com | Other observed source | 1.11% | 21 | 1,895 | C |
| #31 of 501 | Oracle.com | Vendor-owned source | 1.11% | 21 | 1,895 | B |
| #33 of 501 | Mdpi.com | Other observed source | 1.00% | 19 | 1,895 | B |
| #33 of 501 | Nvidia.com | Vendor-owned source | 1.00% | 19 | 1,895 | B |
| #33 of 501 | Quora.com | Community and social platform | 1.00% | 19 | 1,895 | C |
| #36 of 501 | Atlan.com | Vendor-owned source | 0.95% | 18 | 1,895 | B |
| #37 of 501 | Milvus.io | Other observed source | 0.90% | 17 | 1,895 | C |
| #37 of 501 | The New Stack | Editorial publication | 0.90% | 17 | 1,895 | Collecting |
| #39 of 501 | Guideflow.com | Other observed source | 0.84% | 16 | 1,895 | A |
| #40 of 501 | Appinventiv.com | Other observed source | 0.79% | 15 | 1,895 | C |
| #40 of 501 | Truefoundry.com | Vendor-owned source | 0.79% | 15 | 1,895 | B |
| #40 of 501 | Trustradius.com | Market and company database | 0.79% | 15 | 1,895 | C |
| #40 of 501 | Umbrex.com | Other observed source | 0.79% | 15 | 1,895 | C |
| #44 of 501 | Cisco.com | Other observed source | 0.74% | 14 | 1,895 | B |
| #44 of 501 | Digitalapplied.com | Vendor-owned source | 0.74% | 14 | 1,895 | B |
| #44 of 501 | Towardsai.net | Analyst and consulting research | 0.74% | 14 | 1,895 | C |
| #44 of 501 | Zapier.com | Vendor-owned source | 0.74% | 14 | 1,895 | B |
| #48 of 501 | Manageengine.com | Other observed source | 0.69% | 13 | 1,895 | C |
| #48 of 501 | Ovaledge.com | Other observed source | 0.69% | 13 | 1,895 | B |
| #48 of 501 | Zenml.io | Other observed source | 0.69% | 13 | 1,895 | C |
| #51 of 501 | AIMultiple | Editorial publication | 0.63% | 12 | 1,895 | B |
| #51 of 501 | Clarifai.com | Vendor-owned source | 0.63% | 12 | 1,895 | C |
| #51 of 501 | Domo.com | Other observed source | 0.63% | 12 | 1,895 | C |
| #51 of 501 | Github.com | Community and social platform | 0.63% | 12 | 1,895 | A |
| #55 of 501 | Ieee.org | Academic and government source | 0.58% | 11 | 1,895 | B |
| #55 of 501 | Reuters | Editorial publication | 0.58% | 11 | 1,895 | Collecting |
| #55 of 501 | Sap.com | Other observed source | 0.58% | 11 | 1,895 | B |
| #58 of 501 | Nhimg.org | Other observed source | 0.53% | 10 | 1,895 | B |
| #58 of 501 | Northflank.com | Vendor-owned source | 0.53% | 10 | 1,895 | C |
| #58 of 501 | Openai.com | Vendor-owned source | 0.53% | 10 | 1,895 | B |
| #58 of 501 | Openobserve.ai | Vendor-owned source | 0.53% | 10 | 1,895 | C |
| #58 of 501 | Springer.com | Other observed source | 0.53% | 10 | 1,895 | C |
| #58 of 501 | Wikipedia | Academic and government source | 0.53% | 10 | 1,895 | A |
| #58 of 501 | Youtube.com/@cloudcomputinginsider | Other observed source | 0.53% | 10 | 1,895 | Collecting |
| #65 of 501 | Acm.org | Academic and government source | 0.47% | 9 | 1,895 | C |
| #65 of 501 | Cloudflare.com | Other observed source | 0.47% | 9 | 1,895 | C |
| #65 of 501 | Dzone.com | Other observed source | 0.47% | 9 | 1,895 | C |
| #65 of 501 | Getmaxim.ai | Other observed source | 0.47% | 9 | 1,895 | B |
| #65 of 501 | Kanerika.com | Analyst and consulting research | 0.47% | 9 | 1,895 | C |
| #65 of 501 | Mirantis.com | Other observed source | 0.47% | 9 | 1,895 | C |
| #65 of 501 | Stanford.edu | Academic and government source | 0.47% | 9 | 1,895 | C |
| #65 of 501 | Uslegalsupport.com | Other observed source | 0.47% | 9 | 1,895 | Collecting |
| #73 of 501 | Bentoml.com | Other observed source | 0.42% | 8 | 1,895 | C |
| #73 of 501 | Hyland.com | Other observed source | 0.42% | 8 | 1,895 | Collecting |
| #73 of 501 | Introl.com | Other observed source | 0.42% | 8 | 1,895 | C |
| #73 of 501 | Mindstudio.ai | Vendor-owned source | 0.42% | 8 | 1,895 | C |
| #73 of 501 | Qovery.com | Other observed source | 0.42% | 8 | 1,895 | Collecting |
| #73 of 501 | Spheron.network | Other observed source | 0.42% | 8 | 1,895 | B |
| #73 of 501 | Splunk.com | Vendor-owned source | 0.42% | 8 | 1,895 | C |
| #73 of 501 | VentureBeat | Editorial publication | 0.42% | 8 | 1,895 | C |
| #81 of 501 | Ai21.com | Other observed source | 0.37% | 7 | 1,895 | Collecting |
| #81 of 501 | Cohere.com | Other observed source | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Dynatrace.com | Vendor-owned source | 0.37% | 7 | 1,895 | C |
| #81 of 501 | ERP Today | Editorial publication | 0.37% | 7 | 1,895 | Collecting |
| #81 of 501 | Fast.io | Other observed source | 0.37% | 7 | 1,895 | Collecting |
| #81 of 501 | HackerNoon | Other observed source | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Indiatimes | Editorial publication | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Investing.com | Editorial publication | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Meegle.com | Other observed source | 0.37% | 7 | 1,895 | Collecting |
| #81 of 501 | Montecarlo.ai | Other observed source | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Neuraltrust.ai | Other observed source | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Portkey.ai | Other observed source | 0.37% | 7 | 1,895 | Collecting |
| #81 of 501 | Render.com | Other observed source | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Snowflake.com | Vendor-owned source | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Suse.com | Other observed source | 0.37% | 7 | 1,895 | Collecting |
| #81 of 501 | Towardsdatascience.com | Editorial publication | 0.37% | 7 | 1,895 | C |
| #81 of 501 | Vectara.com | Other observed source | 0.37% | 7 | 1,895 | Collecting |
| #98 of 501 | Akamai.com | Other observed source | 0.32% | 6 | 1,895 | C |
| #98 of 501 | Altexsoft.com | Other observed source | 0.32% | 6 | 1,895 | Collecting |
| #98 of 501 | Cast.ai | Other observed source | 0.32% | 6 | 1,895 | C |
Showing the first 100 of 501 ranked sources.
Category leaderboard, pooled across engines: AI Infrastructure
Method
What each engine's figures measure
Release mri_score_v2.1+2026-10-25+9c34b2dccc04; methodology mri_score_v2.1; generated 2026-10-25; window 2026-05-10 to 2026-10-25; artifact 9f1a507f84e8.
The release roster names no model for Google AI Mode.
Google AI Mode's sample is 1,895 observed runs across 119 dates. The evidence floor is 10 observed runs and 7 distinct dates.
ChatGPT runs. They go through OpenAI's API with web search switched on, using the model each release names in its engine roster: gpt-4.1-mini-2025-04-14 in current releases, while earlier runs in the window were answered by gpt-4o-mini-search-preview-2025-03-11. That is the retrieval layer apps and research agents built on OpenAI's API use. The signed-in ChatGPT app answers with its own models and search pipeline and cites differently: a preprint submitted on 2026-10-11 and not yet peer reviewed found that Google Search and OpenAI's API on comparable models together recovered about half of the hostnames ChatGPT Web cited (48.7 and 50.3 percent on two model settings) and 26 to 28 percent of its exact URLs (arXiv 2610.15382v1). Claude, Gemini and Perplexity runs are likewise API runs with web search, on the models the roster names.
Method note, 2026-09-25. From that date, Google AI Mode and Google AI Overviews runs come through a different collection path than earlier runs, with no overlapping days, and answers collected on the two paths differ in how many distinct domains each cites. Per-answer figures for those two engines are read within one side of 2026-09-25, not as a trend across it.
Degraded coverage: 5 of 6 answer engines are currently returning citation-bearing answers. gemini quiet (5 of 20 collected calls produced an observation, 25%). Coverage across the window is uneven: gemini returned citation-bearing answers on 140 of 162 observed days (2,197 of 6,962 returned runs produced a citation); google_ai_mode returned citation-bearing answers on 119 of 162 observed days (1,613 of 2,086 returned runs produced a citation); google_ai_overviews returned citation-bearing answers on 102 of 162 observed days (963 of 1,446 returned runs produced a citation). Engines below 90% of the window are named here; per-engine day and run counts for all 6 are in engine_roster.
Cite this leaderboard
How to cite Google AI Mode · AI Infrastructure
Machine Relations Index (MRI) by Jaxon Parrott, Machine Relations Research — machinerelations.ai. As of October 25, 2026, among sources with a published AI Infrastructure segment, LinkedIn is the most-cited source in Google AI Mode answers across the whole window, cited in 24.59% of 1,895 observed Google AI Mode runs. Release mri_score_v2.1+2026-10-25+9c34b2dccc04. https://machinerelations.ai/index/engines/google_ai_mode/ai-infrastructure. CC BY 4.0.
APA
Parrott, J. (2026). Which sources does Google AI Mode cite most among AI Infrastructure sources? (Version mri_score_v2.1+2026-10-25+9c34b2dccc04) [Data set]. Machine Relations Research. https://machinerelations.ai/index/engines/google_ai_mode/ai-infrastructureBibTeX
@misc{parrott2026mrigoogleaimodeaiinfrastructure,
author = {Parrott, Jaxon},
title = {Which sources does Google AI Mode cite most among AI Infrastructure sources?},
year = {2026},
version = {mri\_score\_v2.1+2026-10-25+9c34b2dccc04},
publisher = {Machine Relations Research},
url = {https://machinerelations.ai/index/engines/google_ai_mode/ai-infrastructure},
license = {CC-BY-4.0},
note = {Machine Relations Index (MRI) by Jaxon Parrott, Machine Relations Research — machinerelations.ai}
}