Nine of fourteen models named Cobalt first on the direct prompt; zero named Raxis. Cobalt was named by fourteen of the fourteen models and Raxis by six and Cobalt carries 47 labels and Raxis 10, 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 penetration testing as a service page.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | RA | |||||
| Grok 4.20 | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | RA | |||||
| 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. Three of four in this category shown.
“Known for pioneer PTaaS delivery. Cobalt connects customers with a vetted network of certified testers (the Cobalt Core) via a modern platform.” Gemini 3.5 Flash · comparative prompt · first choice
“For most mid-market B2B companies, Cobalt and BreachLock tend to offer the strongest combination of quality, speed, and value.” DeepSeek V4 Flash · direct prompt · first choice
“Cobalt.io and Astra Security are top recommendations due to their scalability, compliance support, and ease of use” Mistral Small · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“Raxis or Stingrai offer the best balance of real manual testing, transparent published pricing, and value” DeepSeek V4 Flash · budget prompt · first choice
“Raxis: Top-rated for comprehensive, human-led testing with AI enhancements and continuous options.” Grok 4.20 · paraphrase prompt · alternative
“a boutique such as Atlant Security, Raxis, Packetlabs, or Secarma” Perplexity Sonar · budget 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.