One of fourteen models named Acunetix first on the direct prompt; zero named Burp Suite. Acunetix was named by thirteen of the fourteen models and Burp Suite by thirteen and Acunetix carries 39 labels and Burp Suite 45, so the shares are not directly comparable.
Named in four categories this edition.
Named in three 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, Acunetix and Burp Suite were named in the same answer fifty-five times, of the 125 answers naming Acunetix and the 121 naming Burp Suite. In those answers Burp Suite took the first choice three times and Acunetix three.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | BS | |||||
| GPT-5.4 mini | BS | BS | BS | |||
| Gemini 3.5 Flash | BS | BS | BS | |||
| Perplexity Sonar | ||||||
| Grok 4.1 Fast | BS | |||||
| Mistral Small | BS | BS | ||||
| DeepSeek V4 Flash | BS | |||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | BS | |||||
| Kimi K2 | BS | BS | BS | BS | ||
| GLM 4.7 FlashX | BS | |||||
| MiniMax M2.5 | BS | BS | ||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B | BS |
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 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
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“The Verdict: Avoid for automated scanning. Use only for manual penetration testing.” GLM 4.7 FlashX · negative prompt · hard negative
“Burp Suite Enterprise has complex setup and configuration requirements that often need dedicated security expertise” Claude Haiku 4.5 · negative prompt · soft negative
“Extremely manual and limited automation in the free version; Pro is better but still developer/pentester-focused.” Grok 4.1 Fast · negative prompt · soft negative
“commercial tools like Burp Suite Professional and Invicti catch more vulnerability types than open-source alternatives, with Burp Suite achieving ~29% coverage of critical vulnerabilities” MiniMax M2.5 · comparative prompt · first choice
“I'd generally recommend Burp Suite Professional if you want the best balance of capability, usability, and web-app-focused coverage” GPT-5.4 mini · paraphrase prompt · first choice
“Burp Suite Professional (PortSwigger): Best for manual testing + automated scanning hybrid. Excellent SPA support.” Qwen 3.7 Flash · 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.