Index › IT › Products › GitHub-hosted model repositories · November 2026 Edition
ML platforms · Named, not ranked

GitHub-hosted model repositories

–Too few to rank
1/14Models named it
0First choices
1Warnings
November 2026 Edition · all company sizes counted.
Ranked inML platforms #133 mid-market
What AI models recommend

Named, too few times to rank.

A product needs 10 labels in a category before a share is stated. GitHub-hosted model repositories has 1.

Why models recommend it

No positive label carried a quote.

What gives them pause

“Potential for malicious code or models to be uploaded without review”GLM 4.7 FlashX · Negative question · warning

Also on the shortlist

The products named in the same answers as GitHub-hosted model repositories, over the 1 answer that named it, and how often each was the first choice instead.

A side-by-side page exists where both products are among a category's top eight.

How this is measured

Fourteen AI models from 12 labs are asked the same buying questions six ways, for three company sizes. Standings refresh every edition.

Gane sells AI visibility software. No company can pay to change a result.

Read the method →

Sources returned with these answers

The sites and pages the answers that named GitHub-hosted model repositories came back with. A fact about retrieval, not a cause of the answer.

Fourteen of the fourteen models returned a source list in this edition: five return the pages they cited and nine the search results they consulted. These counts come from 1 of the 1 answers that named GitHub-hosted model repositories and are not a share of its labels.

Domains cited

ai.gov.uk1
appliedai.de1
applyingml.com1
ar5iv.labs.arxiv.org1
arxiv.org1
cyber.gov.au1
debutinfotech.com1
docs.cloud.google.com1
enisa.europa.eu1
eweek.com1

No domain is on file for GitHub-hosted model repositories, so its own site is not marked.

Pages cited

Pages are listed as the models cited them.

By model

How each model answered on GitHub-hosted model repositories across every prompt where it was named for a mid-market B2B company. Fourteen models, six prompts per category.
ModelFirst choiceAlternativeMentionWarningLabels
Claude Haiku 4.500000
GPT-5.4 mini00000
Gemini 3.5 Flash00000
Perplexity Sonar00000
Grok 4.2000000
Mistral Small00000
DeepSeek V4 Flash00000
Llama 4 Maverick00000
Qwen 3.7 Flash00000
Kimi K200000
GLM 4.7 FlashX00011
MiniMax M2.500000
GPT-6 Luna00000
Muse Glimmer 30B00000