Zero of fourteen models named CodeQL first on the direct prompt; zero named Veracode Static Analysis. CodeQL was named by eleven of the fourteen models and Veracode Static Analysis by fourteen and CodeQL carries 27 labels and Veracode Static Analysis 39, so the shares are not directly comparable.
Named in one category this edition.
Named in one category this edition.
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; every quote names the model and the prompt it came from. Both figures come from the static application security testing page.
Across every category in the October 2026 Edition, CodeQL and Veracode Static Analysis were named in the same answer forty-two times, of the 74 answers naming CodeQL and the 138 naming Veracode Static Analysis. In those answers Veracode Static Analysis took the first choice zero times and CodeQL three.
| Model | DirectCO | ParaphraseCO | ComparativeCO | Budget-constrainedCO | Scale-constrainedCO | NegativeCO |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | CO | CO | ||||
| Gemini 3.5 Flash | CO | CO | ||||
| Perplexity Sonar | CO | |||||
| Grok 4.1 Fast | CO | CO | CO | |||
| Mistral Small | CO | |||||
| DeepSeek V4 Flash | CO | CO | CO | CO | ||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | CO | CO | ||||
| Kimi K2 | CO | CO | ||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | CO | CO | CO | CO | ||
| Muse Glimmer 30B | CO | CO |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“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
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“What I'd Avoid for Mid-Market: Checkmarx and Veracode are powerful but typically start at $60K–$100K+/year” Kimi K2 · paraphrase prompt · hard negative
“Full scans can delay fast-moving dev cycles, there's no on-premise option with code upload raising security concerns, and pricing can be steep” Claude Haiku 4.5 · negative prompt · soft negative
“not necessarily the one with the most heavy-duty enterprise compliance rules (like legacy tools Veracode or Fortify)” Gemini 3.5 Flash · direct prompt · soft negative
“the recommended static code security scanner for a mid-sized B2B company could be either Checkmarx or Veracode” Llama 4 Maverick · paraphrase prompt · first choice
“Excels in broad language/framework support (including legacy/binary), whole-app analysis, and enterprise integrations” Grok 4.1 Fast · comparative prompt · alternative
“Highly regulated environments, on-premises requirements, or teams needing very deep taint analysis.” GLM 4.7 FlashX · direct prompt · alternative
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.