Zero of fourteen models named MISP first on the direct prompt; two named Recorded Future Intelligence Cloud. Both were named by all fourteen models and MISP carries 48 labels and Recorded Future Intelligence Cloud 55, 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 threat intelligence platforms page.
Across every category in the November 2026 Edition, MISP and Recorded Future Intelligence Cloud were named in the same answer eighty-nine times, of the 115 answers naming MISP and the 181 naming Recorded Future Intelligence Cloud. In those answers Recorded Future Intelligence Cloud took the first choice seventeen times and MISP fifteen.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.20 | ||||||
| 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 eight in this category shown.
“Sources such as OTX, MISP feeds, PhishTank, and similar services can be useful, but licensing, fair-use, commercial-use, freshness, and accuracy need review” Perplexity Sonar · negative prompt · soft negative
“has had authenticated SQL injection (CVE‑2026‑44381) that can be exploited by an attacker with a valid API key” GLM 4.7 FlashX · negative prompt · soft negative
“Unlike older open-source tools like MISP, OpenCTI offers a modern, graph-based user interface” Gemini 3.5 Flash · paraphrase prompt · soft negative
“MISP is an excellent starting point for organizations building their first threat intelligence program without the budget for commercial TIPs.” Claude Haiku 4.5 · budget prompt · first choice
“Free, community-driven, and transparent about data sources. Best for organizations with internal intelligence capability.” DeepSeek V4 Flash · negative prompt · first choice
“the best threat intelligence (TI) platform is often an open-source or free-tier option like MISP ... or OpenCTI” Grok 4.20 · budget 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.
“small businesses should generally avoid or be cautious about Recorded Future due to its high cost and steep learning curve” Mistral Small · negative prompt · hard negative
“Top-tier threat intelligence platforms (such as Recorded Future, Mandiant, or ThreatConnect) are legitimate, high-quality enterprise tools. However, they can turn into "shelfware"” Gemini 3.5 Flash · negative prompt · soft negative
“Independent user reviews note Recorded Future as complex to navigate with a big learning curve, difficulty creating accurate queries and managing data, and seen inaccuracy.” Muse Glimmer 30B · negative prompt · soft negative
“Broad intelligence coverage, packaged for multiple teams... Uses AI and machine learning to provide real-time threat intelligence” Mistral Small · comparative prompt · first choice
“Frequently ranked 1st in 2026 buyer lists... Broad enterprise coverage and packaging for multiple teams → Recorded Future.” Muse Glimmer 30B · comparative prompt · first choice
“Forrester's 2023 Wave report highlights leaders like Recorded Future and Mandiant (now Google) for overall capability.” Grok 4.20 · comparative 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.