Breach and attack simulation for enterprise buyers
Asked as “breach and attack simulation platform”, and as “security control validation tool”, on behalf of an enterprise B2B company. 59 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each. Added to the October 2026 Edition on October 4, 2026; its answers are read by the distilled judge (ai-indexes-judge-qwen3-14b-run3), not the claude-opus-5 judge of the earlier categories: how the two compare.
Standing · first-choice share
24%
Contested · SafeBreach 22%
24Cymulate22SafeBreach20AttackIQ34others
24% of first choices, contested.
By buyer segment
The same question asked on behalf of a different buyer. Each standing is computed within its segment; they sit side by side and are never added together.
The standing
Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all fourteen models, for an enterprise B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrant
Bars are the share of first choices, 0 to 100Every product with at least 10 labels here. Every product name links to its product page.
For buyers
All twenty-one head-to-head pages: the top seven products, each against each
Cymulate vs AttackIQ FlexCymulate vs AttackIQCymulate vs Horizon3.ai NodeZeroPicus Security Validation Platform vs NodeZeroPicus Security Validation Platform vs PenteraPicus Security Validation Platform vs AttackIQ FlexPicus Security Validation Platform vs AttackIQPicus Security Validation Platform vs Horizon3.ai NodeZeroNodeZero vs PenteraNodeZero vs AttackIQ FlexNodeZero vs AttackIQNodeZero vs Horizon3.ai NodeZeroPentera vs AttackIQ FlexPentera vs AttackIQPentera vs Horizon3.ai NodeZeroAttackIQ Flex vs AttackIQAttackIQ Flex vs Horizon3.ai NodeZeroAttackIQ vs Horizon3.ai NodeZero
Recommended versus criticized
Every product with at least 10 labels here, on both axes. The 30% line names a quadrant, not the verdict above: that one needs more than 40%.
Criticized challengerCriticized default
Negative label rate →
01
02
03
04
05M06
07Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Cymulate24%
Cymulate24%02SafeBreach22%
SafeBreach22%03AttackIQ20%
AttackIQ20%04Picus Security Validation Platform15%
Picus Security Validation Platform15%05Pentera7%
Pentera7%06Mandiant Security Validation3%
07XM Cyber2%
XM Cyber2%What they warned about
One of fourteen models held their first choice under the paraphrase. 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, GLM 4.7 FlashX, MiniMax M2.5, GPT-6 Luna and Muse Glimmer 30B changed. A high negative share on a product with few labels is a warning. A low share on a product with many labels is salience, not sentiment.
AttackIQ14%
8 of 59 labels negative · 8 of 14 models
“some enterprise-level reviews suggest the platform may **lack the depth required for massive, highly complex environments**” Qwen 3.7 Flash, negative prompt
Cymulate17%
10 of 58 labels negative · 8 of 14 models
“**Cymulate** (and similar heavy-cloud tools) has faced criticism in specific enterprise forums regarding **integration stability** and **alert inefficiencies**” Qwen 3.7 Flash, negative prompt
SafeBreach14%
8 of 57 labels negative · 8 of 14 models
“SafeBreach has historically been viewed as complex to deploy and manage at scale, with users reporting "cumbersome navigation" and high overhead” Claude Haiku 4.5, negative prompt
Mandiant Security Validation
20%
3 of 15 labels negative · 3 of 14 models · 2 hard negative
“Google/Mandiant themselves declared "BAS activities are now outdated" back in 2021 ... starts at $100,000+/year, making it expensive for uncertain value” Kimi K2, negative prompt
What they cite
Citations exist only for the models that return a source list: fourteen of the fourteen in this edition, and all six flagship models on the expanded tier.
Sites the answers cite
79 of 84 answers in this category came back with a source list, from 14 of 14 models: citations where the model returns them, or the search results it consulted. 1211 links across 240 sites, every framing counted. Ranked by the number of answers carrying the site or page. None of the 252 answers across every segment cited this index's own page for the category.
vendor site · Picus Security47 answers · 87 citations · 14 models
vendor site · Guideflow45 answers · 47 citations · 11 models
39 answers · 39 citations · 12 models
30 answers · 30 citations · 11 models
vendor site · Cymulate29 answers · 47 citations · 12 models
vendor site · SafeBreach29 answers · 44 citations · 12 models
27 answers · 32 citations · 12 models
vendor site · Adaptive Security27 answers · 27 citations · 11 models
vendor site · G226 answers · 34 citations · 11 models
26 answers · 32 citations · 9 models
24 answers · 27 citations · 10 models
23 answers · 31 citations · 12 models
Pages the answers cite
The ten pages named in the most answers, by full address. A page here is one the models returned with a recommendation, not one the index endorses.
41 answers · 11 models
39 answers · 12 models
30 answers · 11 models
26 answers · 11 models
23 answers · 10 models
21 answers · 9 models
21 answers · 11 models
20 answers · 8 models
15 answers · 10 models
15 answers · 8 models
Search against answers
Each company's standing in the answers beside its site's footprint in Google search, one row a site: the products the models named on it with their shares, and the share they add up to; monthly searches on Google, and DataForSEO's estimate of AI search demand (modeled from search signals, directional, not a count of queries to any assistant), for the most-searched of the company's and its products' names (the name is in each row's hover text); estimated monthly organic visits to the site; and its best position in Google's top ten for “best breach and attack simulation platform”, “breach and attack simulation platform”, “breach and attack simulation platforms”. US estimates from DataForSEO and Google's Ads Transparency Center. A small company's site, or a mid-sized company's site for its flagship, is marked company; a product on a large parent's site (Google, Microsoft) has no site figures. A column with no figures for this category is left out, and an empty cell means none were seen, not none exist. Two measurements side by side: neither is read as the cause of the other.
| Company and products | Share | Own site cited | Name searches, Google | AI search demand, est. | Organic visits | Paid search a month, est. | Google ads, last 30 days | Best Google position |
|---|---|---|---|---|---|---|---|---|
| SafeBreach safebreach.com SafeBreach 22%, SafeBreach Validate 3% | 25% | 137 | 480 | 3 | 1,058 | 8 | 1 | |
| Cymulate cymulate.com | 24% | 163 | 720 | 16 | 16,407 | 3 | ||
| AttackIQ attackiq.com AttackIQ 20%, AttackIQ Flex 2% | 22% | 124 | 1,000 | 9 | 1,414 | 11 | ||
| Picus Security Validation Platform picussecurity.com | 15% | 148 | 20 | 0 | 81,880 | $1,031 | 25 | 3 |
| Pentera pentera.io | 7% | 101 | 1,900 | 49 | 9,580 | 0 | ||
| Mandiant cloud.google.com Mandiant Security Validation 3% | 3% | 31 | 6,600 | 253 | 7,405,347 company | |||
| XM Cyber xmcyber.com | 2% | 41 | 590 | 12 | 2,524 | 0 | ||
| Vanta vanta.com | 2% | 500 | 40,500 | 1,219 | 72,260 | 120 | ||
| Horizon3.ai horizon3.ai Horizon3.ai NodeZero 0% | 0% | 36 | 40 | 1 | 7,505 company | $431 | 7 | |
| SCYTHE scythe.io | 0% | 7 |
Google's top ten for the three searches hold 19 sites; 4 of them are among the sites the models cited here (g2.com, picussecurity.com, safebreach.com, startupstash.com). The first result for “best breach and attack simulation platform” is sourceforge.net.
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.ShowHide
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.
ShowHideModelDirect“What is the best breach and attack simulation platform for an enterprise B2B company?”Paraphrase“Which security control validation tool would you recommend to a large B2B company with thousands of employees?”Comparative“What are the top enterprise-grade breach and attack simulation platforms and how do they differ?”Budget-constrained“What is the best breach and attack simulation platform for a large company that needs predictable total cost across thousands of users?”Scale-constrained“We are a 5,000 person company with SSO, SOC 2 and procurement review requirements evaluating a breach and attack simulation platform. What should we look at?”Negative“Which breach and attack simulation platforms should a large enterprise avoid or be cautious about?”
Claude Haiku 4.5Cymulateno first choiceChangedThe NodeZero PlatformCymulateno first choiceagainst: AttackIQ, Cymulate, SafeBreach
Two alternatives
AttackIQ, SafeBreachSix alternatives
Adaptive Security, AttackIQ, Cymulate, Pentera, SafeBreach, XM CyberTwo alternatives
SafeBreach, XM CyberGPT-5.4 miniAttackIQagainst: Mandiant Security ValidationPicus Security Validation Platform, SafeBreachChangedAttackIQAttackIQagainst: Cymulateno first choicenothing named
Two alternatives
Cymulate, Picus Security Validation PlatformThree alternatives
AttackIQ, Pentera, Tenable OneFive alternatives
Cymulate, Nemesis, NetSPI BAS, Picus Security Validation Platform, SafeBreachTwo alternatives
Picus Security Validation Platform, SafeBreachGemini 3.5 FlashXM CyberCymulateChangedCymulateSafeBreachagainst: Cymulate, PenteraAttackIQ, SafeBreachagainst: Atomic Red Team, AttackIQ, Cymulate, MITRE Caldera, Pentera, SafeBreach, XM Cyber
Four alternatives
AttackIQ, Cymulate, Picus Security Validation Platform, SafeBreachThree alternatives
Mandiant Security Validation, Pentera, SafeBreachSix alternatives
AttackIQ, Pentera, Picus Security Validation Platform, SCYTHE, SafeBreach, XM CyberOne alternative
AttackIQThree alternatives
Cymulate, Picus Security Validation Platform, XM CyberPerplexity SonarSafeBreachMandiant Security ValidationChangedSafeBreachSafeBreachagainst: rThreatno first choiceagainst: BreachBits, FirstStrike, rThreat
Three alternatives
Cymulate, Pentera, Picus Security Validation PlatformTwo alternatives
Cymulate, SafeBreachFour alternatives
AttackIQ, Cymulate, Pentera, Picus Security Validation PlatformOne alternative
PenteraGrok 4.1 FastCymulate, Picus Security Validation PlatformVantaChangedCymulate, Picus Security Validation PlatformPicus Security Validation Platformagainst: Mandiant Security Validation, PenteraCymulateagainst: AttackIQ, FortiTester
Three alternatives
AttackIQ, Pentera, SafeBreachSix alternatives
Cymulate, Drata, Hyperproof, OneTrust, SafeBreach, SecureframeThree alternatives
AttackIQ, SafeBreach, XM CyberThree alternatives
AttackIQ, Cymulate, SafeBreachThree alternatives
AttackIQ, Picus Security Validation Platform, SafeBreachMistral SmallAttackIQ, PenteraAttackIQChangedAttackIQAttackIQagainst: Cymulate, SafeBreachSafeBreachagainst: AttackIQ, Cymulate
One alternative
CymulateOne alternative
Picus Security’s Security Validation PlatformFive alternatives
Cymulate, Picus Security Validation Platform, SafeBreach, Validato, XM CyberFour alternatives
AttackIQ, IBM Randori, PlexTrac, SCYTHEDeepSeek V4 FlashAttackIQ, CymulateSafeBreachChangedCymulate, SafeBreachSafeBreachAttackIQ, SafeBreachagainst: Picus Security Validation Platform, SafeBreach
Two alternatives
Picus Security Validation Platform, SafeBreachOne alternative
CymulateFive alternatives
AttackIQ, Fortinet FortiTester, Mandiant Security Validation, Picus Security Validation Platform, XM CyberTwo alternatives
AttackIQ, CymulateTwo alternatives
Cymulate, Picus Security Validation PlatformLlama 4 MaverickAttackIQ, PenteraMandiant Security ValidationChangedno first choiceno first choiceno first choiceagainst: AttackIQ
Four alternatives
Cymulate Exposure Validation Platform, Picus Security Control Validation, SafeBreach Security Control Validation, Validato Security Controls ValidationQwen 3.7 FlashCymulate, Pentera, SafeBreachPentera, Picus Security Validation PlatformChangedagainst: Proofpoint Threat Responseno first choicePicus Security Validation Platformagainst: SafeBreachno first choiceagainst: AttackIQ, Cymulate, Picus Security Validation Platform
Four alternatives
AttackIQ, Horizon3.ai NodeZero, Picus Security Validation Platform, XM CyberOne alternative
CymulateKimi K2CymulateCymulateHeldAttackIQPicus Security Validation Platformno first choiceagainst: AttackIQ, Cymulate, Mandiant Security Validation, SafeBreach
Three alternatives
AttackIQ, Picus Security Validation Platform, SafeBreachTwo alternatives
Mandiant Security Validation, Picus Security Validation PlatformSix alternatives
Cymulate, Horizon3.ai NodeZero, Pentera, Picus Security Validation Platform, SafeBreach, XM CyberTwo alternatives
AttackIQ, CymulateGLM 4.7 FlashXCymulatePicus Security Validation PlatformChangedPenteraAttackIQ Flexno first choicenothing named
Six alternatives
AttackIQ, Palo Alto Networks Cortex EM, Pentera, Picus Security Validation Platform, SafeBreach, Tenable OneThree alternatives
Mandiant Security Validation, Pentera, SafeBreachFive alternatives
AttackIQ, Cymulate, Mandiant Security Validation, SafeBreach, XM CyberTwo alternatives
Picus Security Validation Platform, Rapid7 InsightVMMiniMax M2.5no first choicePicus Security Validation Platform, SafeBreachChangedSafeBreachAttackIQ, Cymulate, SafeBreachSafeBreach Validateagainst: Atomic Red Team, AttackIQ, Caldera, Cymulate, Picus Security Validation Platform, SafeBreach
Three alternatives
AttackIQ, Cymulate, NetSPIThree alternatives
AttackIQ, Cymulate, PenteraGPT-6 LunaCymulate, Picus Security Validation PlatformSafeBreach ValidateChangedAttackIQ, Cymulate, Picus Security Validation Platform, SafeBreachAttackIQagainst: AttackIQ Flexno first choiceagainst: Cymulate, Pentera, SafeBreach
Two alternatives
AttackIQ, SafeBreachTwo alternatives
AttackIQ, Picus Security Validation PlatformTwo alternatives
Pentera, SCYTHEOne alternative
Microsoft Defender for Office 365 Plan 2Muse Glimmer 30BCymulate, SafeBreachAttackIQChangedAttackIQ, CymulateCymulateagainst: Microsoft Defender for Endpointno first choicenothing named
Four alternatives
AttackIQ, Pentera, Picus Security Validation Platform, XM CyberOne alternative
Picus Autonomous Exposure Validation PlatformFour alternatives
Pentera, Picus Security Validation Platform, SafeBreach, XM CyberThree alternatives
AttackIQ, Picus Security Validation Platform, SafeBreachBold is the first choiceAlternatives are counted; the count opens them.What the answer argued against
The record
One row per call: the version string exactly as returned, whether the model searched, sources cited, and latency. Full answer text is in the free responses file. Download the record
Eighty-four rows: every prompt, every model, every answer.
| Prompt | Model | Version string | Time (UTC) | Searched | Sources | Latency |
|---|---|---|---|---|---|---|
| Direct recommendation | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-05 01:43 | yes | 9 | 6 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 22:56 | yes | 2 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 00:44 | yes | 12 | 25 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-05 00:16 | yes | 29 | 4 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 23:07 | yes | 25 | 10 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 00:23 | yes | 10 | 7 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 01:27 | yes | 22 | 34 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 00:42 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 00:04 | yes | 19 | 65 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 00:48 | yes | 18 | 22 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 01:54 | yes | 14 | 35 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:18 | yes | 5 | 13 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-04 23:55 | yes | 5 | 22 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 00:52 | yes | 23 | 27 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 22:46 | no | 0 | 4 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 22:10 | yes | 5 | 6 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 00:31 | yes | 12 | 27 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-05 01:40 | yes | 34 | 3 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 23:44 | yes | 22 | 8 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 01:24 | yes | 5 | 3 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 00:18 | yes | 23 | 46 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 22:16 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:11 | yes | 10 | 19 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 23:40 | yes | 18 | 20 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 00:51 | yes | 15 | 17 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 01:32 | yes | 5 | 21 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-04 23:42 | yes | 3 | 14 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 00:06 | yes | 24 | 31 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-05 01:05 | yes | 14 | 10 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 23:22 | yes | 7 | 11 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 01:06 | yes | 18 | 30 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-05 01:48 | yes | 17 | 4 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 01:26 | yes | 22 | 12 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 01:11 | yes | 25 | 17 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 01:46 | yes | 22 | 103 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 22:31 | yes | 5 | 3 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:42 | yes | 5 | 27 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 00:13 | yes | 20 | 30 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 00:23 | yes | 25 | 55 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:05 | yes | 22 | 37 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-05 00:51 | yes | 7 | 27 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 23:21 | yes | 20 | 31 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-05 01:19 | yes | 18 | 10 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 22:14 | yes | 5 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 22:44 | yes | 19 | 29 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-05 01:43 | yes | 17 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:52 | yes | 20 | 14 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 00:19 | yes | 5 | 3 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 01:12 | yes | 21 | 19 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:06 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 00:19 | yes | 10 | 41 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 00:35 | yes | 20 | 47 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 01:52 | yes | 22 | 22 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:44 | yes | 13 | 44 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-04 22:29 | yes | 3 | 17 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 01:16 | yes | 20 | 31 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-05 00:24 | yes | 27 | 13 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 00:07 | yes | 0 | 11 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 00:41 | no | 0 | 16 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-05 00:52 | yes | 17 | 5 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:47 | yes | 19 | 11 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 00:48 | no | 0 | 10 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 00:14 | yes | 23 | 70 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:06 | yes | 5 | 4 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 23:31 | no | 0 | 24 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 22:45 | yes | 24 | 38 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 01:00 | yes | 25 | 31 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 22:25 | yes | 9 | 14 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-04 23:02 | yes | 3 | 29 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 00:56 | yes | 15 | 32 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-05 00:53 | yes | 24 | 11 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 00:34 | yes | 4 | 6 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 00:18 | yes | 14 | 28 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-05 00:45 | yes | 20 | 4 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:39 | yes | 21 | 11 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 01:25 | yes | 14 | 6 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 23:50 | yes | 22 | 43 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 23:51 | yes | 5 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:31 | yes | 19 | 55 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 01:01 | yes | 23 | 33 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 01:18 | yes | 22 | 49 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 01:04 | yes | 22 | 100 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-05 01:34 | yes | 5 | 25 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 00:59 | yes | 23 | 30 s |
Normalization in this category
Every judgment call made between the raw labels and the numbers above, listed so it is visible and reversible.
ShowHide
Category-scoped readings
Horizon3.ai read as Horizon3.ai NodeZero
Horizon3.ai (NodeZero) read as Horizon3.ai NodeZero
Mandiant read as Mandiant Security Validation
Picus read as Picus Security Validation Platform
Picus Security read as Picus Security Validation Platform
Unresolved, counted raw
AttackIQ Platform
BreachBits
Cymulate Exposure Validation Platform
FourCore
Keysight Threat Simulator / ReliaQuest GreyMatter
Mandiant Red Team Assessment
NetSPI Breach and Attack Simulation
Palo Alto Networks Cortex EM
Picus BAS
Picus Security Control Validation
Picus Security’s Security Validation Platform
Prisma Secure
Proofpoint Threat Response
RedMimicry
RedScan Breach and Attack Simulation
ReliaQuest GreyMatter Verify
SafeBreach Breach and Attack Simulation Platform
SafeBreach Security Control Validation
Silent Armor
Validato Security Controls Validation
Verodin
Discontinued, still offered
No shut-down product was recommended here.