# Snyk vs CodeQL: which do AI models recommend for SAST, October 2026

IT AI Recommendation Index, October 2026 Edition, Static application security testing. Two of fourteen models named Snyk first on the direct prompt; zero named CodeQL. Page: https://it-ai-index.com/developer/static-application-security-testing/snyk-vs-codeql/

| | First-choice share | Rank | Negative rate | Labels | Models naming it |
|---|---|---|---|---|---|
| Snyk | 8% | #4 of 10 | 9% | 11 | 7 of 14 |
| CodeQL | 4% | #5 of 10 | 11% | 27 | 11 of 14 |

## The direct prompt, model by model

- Mistral Small: snyk first (first choices: Snyk) (alternatives: Aikido Security, Semgrep)
- MiniMax M2.5: snyk first (first choices: Snyk) (alternatives: Semgrep, Veracode Static Analysis)
- GPT-6 Luna: neither first, one named (first choices: Semgrep) (alternatives: GitHub Advanced Security, Snyk)
- Claude Haiku 4.5: neither named
- GPT-5.4 mini: neither named (first choices: Semgrep) (alternatives: Checkmarx One, Snyk Code, Veracode Static Analysis)
- Gemini 3.5 Flash: neither named (first choices: Aikido Security) (alternatives: GitHub Advanced Security, GitLab SAST, Semgrep, Snyk Code)
- Perplexity Sonar: neither named (first choices: Semgrep) (alternatives: Checkmarx One, Snyk Code)
- Grok 4.1 Fast: neither named (first choices: Snyk Code) (alternatives: Semgrep, SonarQube)
- DeepSeek V4 Flash: neither named (first choices: Snyk Code) (alternatives: CodeAnt.ai, Semgrep, SonarQube)
- Llama 4 Maverick: neither named (first choices: Snyk Code)
- Qwen 3.7 Flash: neither named (first choices: SonarQube) (alternatives: Semgrep, Snyk Code)
- Kimi K2: neither named (first choices: Semgrep, Snyk Code) (alternatives: SonarQube)
- GLM 4.7 FlashX: neither named (first choices: SonarQube) (alternatives: Checkmarx One, Codacy, DeepSource, GitHub Advanced Security, OpenText Fortify, Semgrep, Snyk Code, Veracode Static Analysis)
- Muse Glimmer 30B: neither named (first choices: SonarQube) (alternatives: Semgrep)

## What the models said about Snyk

- ""We are forced to use Snyk–it's basically infuriating support and false positives... it's also insanely expensive"" (Claude Haiku 4.5, negative prompt, soft negative)
- "Snyk appears to be the most frequently recommended option for mid-market B2B companies running modern stacks" (MiniMax M2.5, direct prompt, first choice)

## What the models said about CodeQL

- "CodeQL requires a subscription to GitHub Advanced Security (GHAS), which is highly enterprise-focused and expensive" (Gemini 3.5 Flash, budget prompt, soft negative)
- "CodeQL (A "Proceed with Caution" for Closed-Source Teams) ... GHAS licensing, which can be prohibitively expensive" (Gemini 3.5 Flash, negative prompt, soft negative)
- "CodeQL if your stack or plan doesn't fit: Check language support before adopting it" (GPT-6 Luna, negative prompt, soft negative)
- "GitHub CodeQL – Free for public repositories ... It provides deep code analysis and is widely used for finding vulnerabilities in multiple languages." (Mistral Small, budget prompt, first choice)
- "my default recommendation would be GitHub CodeQL if you already use GitHub" (GPT-5.4 mini, paraphrase prompt, first choice)
- "Lower noise: CodeQL (semantic, low FPs)" (Grok 4.1 Fast, negative prompt, first choice)

Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen models, for a mid-market B2B company; rank is within the category. Comparisons are drawn for the top eight products in each category. Published under CC BY 4.0; the output is the models' output, and nothing here is a recommendation by the index.