Five of fourteen models named Invicti first on the direct prompt; one named Acunetix. Invicti was named by fourteen of the fourteen models and Acunetix by thirteen and Invicti carries 43 labels and Acunetix 39, so the shares are not directly comparable.
Named in three categories this edition.
Named in four categories 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 dynamic application security testing page.
Across every category in the October 2026 Edition, Invicti and Acunetix were named in the same answer sixty-four times, of the 142 answers naming Invicti and the 125 naming Acunetix. In those answers Acunetix took the first choice one time and Invicti twenty-three.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| 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. Five of six in this category shown.
“Invicti has had GUI scan bugs observed at times and slows down while scanning large applications” Claude Haiku 4.5 · negative prompt · soft negative
“Quote-only (enterprise skew) | Exploit confirmation; scales well but pricier” Grok 4.1 Fast · paraphrase prompt · soft negative
“Invicti is considered the best DAST tool for most mid-market enterprises, with proof-based scanning that eliminates false-positive triage” Claude Haiku 4.5 · direct prompt · first choice
“Combines DAST with IAST, excels at identifying vulnerabilities in web apps and APIs, and is known for high accuracy and low false positives.” Mistral Small · comparative prompt · first choice
“commercial tools like Burp Suite Professional and Invicti catch more vulnerability types than open-source alternatives” MiniMax M2.5 · comparative 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.
“excellent for complex web applications with 12,000+ vulnerability types, but has a premium price and potential for false positives” Claude Haiku 4.5 · comparative prompt · soft negative
“The Verdict: Use with caution. It is a popular commercial tool, but it is notorious for being "noisy."” GLM 4.7 FlashX · negative prompt · soft negative
“Legacy versions struggle with SPAs, CAPTCHAs, and complex auth, leading to shallow coverage and noise.” Grok 4.1 Fast · negative prompt · soft negative
“my recommendation is Acunetix if you want a strong balance of broad web scanning, automation, and mid-market fit” Perplexity Sonar · paraphrase prompt · first choice
“For a B2B company specifically, I'd lean toward Acunetix due to its strong API security testing capabilities” MiniMax M2.5 · paraphrase prompt · first choice
“If you want one name: Acunetix by Invicti is the safest recommendation for most mid-market B2B companies.” GPT-5.4 mini · direct 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.