Four of fourteen models named Semgrep first on the direct prompt; zero named CodeQL. Semgrep was named by fourteen of the fourteen models and CodeQL by eleven and Semgrep carries 63 labels and CodeQL 27, so the shares are not directly comparable.
Named in three categories 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, Semgrep and CodeQL were named in the same answer seventy times, of the 208 answers naming Semgrep and the 74 naming CodeQL. In those answers CodeQL took the first choice three times and Semgrep thirty-two.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | CO | |||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.1 Fast | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
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.
“Semgrep OSS and Bandit are fast and low false-positive for obvious patterns, but miss vulnerabilities that span multiple functions... insufficient as sole nightly security scanners” Muse Glimmer 30B · negative prompt · soft negative
“Semgrep Community Edition as your only deep security scanner: It can be useful for fast checks and custom rules, but its analysis is limited to a file/function context” GPT-6 Luna · negative prompt · soft negative
“Checkmarx, Veracode, and Semgrep have all struggled with this because their rule-based engines flag anything that could be a vulnerability” Claude Haiku 4.5 · negative prompt · soft negative
“Semgrep as the primary scanner across all languages... For most budget-constrained companies, Semgrep OSS + SonarQube Community Edition... is the most commonly recommended starting point” Muse Glimmer 30B · budget prompt · first choice
“Tools like Semgrep are generally preferred for modern CI/CD because they are lightweight, customizable, and run significantly faster.” GLM 4.7 FlashX · negative prompt · first choice
“look for developer-friendly alternatives like Semgrep, where rules are written in YAML and read like standard code” Gemini 3.5 Flash · negative prompt · first choice
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
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.