Breach and attack simulation
Asked as “breach and attack simulation platform”, and as “security control validation tool”, on behalf of a mid-market B2B company. 58 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 · Picus Security Validation Platform 17%
24Cymulate17Picus Security Validation Platform12NodeZero47others
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 a mid-market B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrantSince September 2026
02
Picus Security Validation Platform17%6%49accepted challengernewNew since September 2026: not ranked then, 17% now.
Picus Security Validation Platform17%6%49accepted challengernewNew since September 2026: not ranked then, 17% now.07
Horizon3.ai NodeZero2%8%12accepted challengernewNew since September 2026: not ranked then, 2% now.
Horizon3.ai NodeZero2%8%12accepted challengernewNew since September 2026: not ranked then, 2% now.Show the two products at 0%, ordered by negative rate
The floor is 11 points of share, measured: how far the models move a leader on their own when the same questions are asked twice with nothing changed. A larger change is movement; a smaller one is noise, and both are shown. Movement is read over the twelve models both editions asked; GPT-6 Luna, Muse Glimmer 30B joined this edition and are in the standing but not yet in the comparison. How the floor is measured
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.
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 →
0102N03
04
05
0607
08
09Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Cymulate24%
Cymulate24%02Picus Security Validation Platform17%
Picus Security Validation Platform17%03NodeZero12%
04Pentera7%
Pentera7%05AttackIQ Flex7%
AttackIQ Flex7%06AttackIQ2%
AttackIQ2%07Horizon3.ai NodeZero2%
Horizon3.ai NodeZero2%08XM Cyber0%
XM Cyber0%09SafeBreach0%
SafeBreach0%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, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, 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.
SafeBreach33%
15 of 46 labels negative · 10 of 14 models · 2 hard negative
“Avoid if you are not a large enterprise with a mature security operations team and a six-figure budget for security validation.” DeepSeek V4 Flash, negative prompt
Cymulate21%
11 of 53 labels negative · 8 of 14 models
“some enterprise users have noted that its dynamic reporting, user interface complexity, and third-party SIEM/EDR integrations can occasionally be unstable” Gemini 3.5 Flash, negative prompt
AttackIQ24%
9 of 38 labels negative · 7 of 14 models · 1 hard negative
“**Avoid:** AttackIQ and SafeBreach tend to be priced higher and are better suited for larger enterprises” Kimi K2, direct prompt
Pentera28%
9 of 32 labels negative · 7 of 14 models
“Industry-standard vendors like Cymulate or Pentera typically charge $50k–$100k+ annually, making them inaccessible for tight budgets.” Qwen 3.7 Flash, budget 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
76 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. 1066 links across 210 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 · Guideflow48 answers · 50 citations · 11 models
vendor site · Picus Security44 answers · 82 citations · 12 models
40 answers · 40 citations · 12 models
vendor site · G228 answers · 42 citations · 12 models
vendor site · Adaptive Security28 answers · 28 citations · 11 models
vendor site · Cymulate25 answers · 34 citations · 10 models
25 answers · 27 citations · 11 models
24 answers · 30 citations · 12 models
20 answers · 20 citations · 11 models
19 answers · 23 citations · 11 models
vendor site · FitGap19 answers · 23 citations · 10 models
19 answers · 19 citations · 11 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
40 answers · 12 models
28 answers · 11 models
23 answers · 11 models
20 answers · 11 models
19 answers · 11 models
17 answers · 11 models
16 answers · 8 models
14 answers · 7 models
14 answers · 10 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 |
|---|---|---|---|---|---|---|---|---|
| Cymulate cymulate.com | 24% | 163 | 720 | 16 | 16,407 | 3 | ||
| Picus Security Validation Platform picussecurity.com | 17% | 148 | 20 | 0 | 81,880 | $1,031 | 25 | 3 |
| NodeZero | 12% | 720 | 15 | |||||
| Infection Monkey | 9% | 880 | 11 | |||||
| AttackIQ attackiq.com AttackIQ Flex 7%, AttackIQ 2% | 9% | 124 | 1,000 | 9 | 1,414 | 11 | ||
| Pentera pentera.io | 7% | 101 | 1,900 | 49 | 9,580 | 0 | ||
| MITRE Caldera mitrecaldera.com | 3% | 12 | 390 | 10 | 0 | |||
| OpenBAS openbas.io | 3% | 18 | 90 | 2 | ||||
| Horizon3.ai horizon3.ai Horizon3.ai NodeZero 2% | 2% | 36 | 40 | 1 | 7,505 company | $431 | 7 | |
| Drata drata.com | 2% | 390 | 9,900 | 257 | 36,413 | 54 |
Google's top ten for the three searches hold 19 sites; 3 of them are among the sites the models cited here (g2.com, picussecurity.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 a mid-market B2B company?”Paraphrase“Which security control validation tool would you recommend to a mid-sized B2B company?”Comparative“What are the top breach and attack simulation platforms and how do they differ?”Budget-constrained“What is the best breach and attack simulation platform for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a breach and attack simulation platform. What should we look at?”Negative“Which breach and attack simulation platforms should I avoid or be cautious about?”
Claude Haiku 4.5CymulateOpenVAS, Tenable NessusChangedno first choiceInfection Monkeyno first choiceagainst: AttackIQ, Pentera, SafeBreach
Two alternatives
AttackIQ, PenteraSix alternatives
Lacework, Orca Security, Qualys, Rapid7 InsightVM, Tenable Compliance, WizSeven alternatives
AttackIQ, First Strike, Horizon3.ai NodeZero, MITRE Caldera, OpenBAS, Picus Security Validation Platform, Prelude OperatorGPT-5.4 miniCymulateAttackIQChangedno first choiceAttackIQ Flexagainst: Pentera, SafeBreachno first choiceagainst: NetSPI
Two alternatives
Pentera, Picus Security Validation PlatformFour alternatives
Cymulate, Horizon3.ai NodeZero, Picus Security Validation Platform, SafeBreachOne alternative
Picus Security Validation PlatformGemini 3.5 FlashPicus Security Validation PlatformCymulateChangedCymulate, SafeBreachOpenAEV (formerly OpenBAS) by Filigranagainst: Pentera, SafeBreach, XM CyberCymulate, Horizon3.ai NodeZero, Pentera, Picus Security Validation Platformagainst: AttackIQ, Cymulate, MITRE Caldera, SafeBreach
Two alternatives
Cymulate, Horizon3.ai NodeZeroTwo alternatives
Horizon3.ai NodeZero, Picus Security Validation PlatformFive alternatives
AttackIQ, Pentera, Picus Security Validation Platform, SCYTHE, XM CyberFour alternatives
Atomic Red Team, BreachLock, Cymulate, MITRE CalderaPerplexity SonarPicus Security Validation PlatformPenteraChangedNodeZero, PenteraNodeZero, Picus Security Validation Platformagainst: Cymulate, SafeBreachno first choicenothing named
Two alternatives
Cymulate, NodeZeroThree alternatives
Drata, Secureframe, SprintoSeven alternatives
Adaptive Security, Akamai Guardicore Segmentation, AttackIQ, Cymulate, Picus Security Validation Platform, SafeBreach, XM CyberGrok 4.1 FastCymulateagainst: SafeBreachPenteraChangedCymulateMITRE Calderaagainst: Horizon3.ai NodeZero, Picus Security Validation PlatformCymulateagainst: AttackIQ, Cymulate
Three alternatives
AttackIQ, NodeZero, Picus Security Validation PlatformFour alternatives
Drata, Secureframe, Sprinto, VantaFive alternatives
AttackIQ, Pentera, Picus Security Validation Platform, SafeBreach, XM CyberFour alternatives
Atomic Red Team, AttackIQ Flex, Infection Monkey, OpenBASFour alternatives
AttackIQ, Pentera, Picus Security Validation Platform, SafeBreachMistral SmallCymulatePenteraChangedAttackIQNodeZero, Picus Security Validation Platformagainst: AttackIQ, Cymulate, Mandiant Security Validation, Penterano first choiceagainst: AttackIQ, Cymulate, FortiTester, SafeBreach
One alternative
WesethThree alternatives
Pentera, RidgeBot, XM CyberOne alternative
Aqua Security TrivyDeepSeek V4 FlashCymulateagainst: Pentera, SafeBreachCymulateHeldagainst: Mandiant Security Validation, SafeBreachCymulateAttackIQ FlexCymulateagainst: Penteraagainst: AttackIQ, Cisco, Cymulate, FortiTester, Picus Security Validation Platform, SafeBreach
Two alternatives
AttackIQ, Picus Security Validation PlatformTwo alternatives
AttackIQ, Picus Security Validation PlatformSix alternatives
AttackIQ, Horizon3.ai NodeZero, Pentera, Picus Security Validation Platform, SafeBreach, XM CyberTwo alternatives
Horizon3.ai NodeZero, Picus Security Validation PlatformThree alternatives
AttackIQ, Picus Security Validation Platform, SafeBreachLlama 4 MaverickValidatono first choiceChangedno first choiceNodeZero, Picus Security Validation Platformno first choicenothing named
One alternative
WesethQwen 3.7 FlashNodeZeroagainst: SafeBreachDrata, VantaChangedagainst: OneTrust GRC, ServiceNow Integrated Risk ManagementSCYTHEOpenBASagainst: Cymulate, Penterano first choiceagainst: AttackIQ Flex, Cymulate
Two alternatives
Cymulate, Picus Security Validation PlatformThree alternatives
Pentera, Secureframe, Tenable Vulnerability ManagementThree alternatives
Cymulate, Picus Security Validation Platform, SafeBreachFive alternatives
Astra Security, Infection Monkey, MITRE Caldera, OpenAEV, ValidatoKimi K2NodeZeroagainst: AttackIQ, SafeBreachCymulateChangedSafeBreachAttackIQ Flex, Infection Monkey, MITRE Calderaagainst: Cymulate, Pentera, Picus Security Validation Platform, SafeBreachno first choiceagainst: AttackIQ, Cymulate, Pentera, SafeBreach
Two alternatives
Cymulate, Picus Security Validation PlatformTwo alternatives
Pentera, Picus Security Validation PlatformFour alternatives
AttackIQ, Cymulate, Pentera, Picus Security Validation PlatformTwo alternatives
Atomic Red Team, ValidatoGLM 4.7 FlashXNodeZero, Picus Security Validation PlatformPicus Security Validation PlatformChangedCymulateInfection Monkeyno first choicenothing named
Four alternatives
AttackIQ, Cymulate, Pentera, SafeBreachThree alternatives
AttackIQ, Cymulate, SafeBreachFour alternatives
AttackIQ, Dragos, Picus Security Validation Platform, SafeBreachFour alternatives
AttackIQ Flex, FirstStrike, Nemesis, OpenBASMiniMax M2.5Cymulate, NodeZeroAttackIQ Adversarial Exposure Validation, Picus Security Validation PlatformChangedCymulateInfection Monkeyno first choicenothing named
One alternative
AttackIQFour alternatives
Cymulate, Drata, SafeBreach, VantaFour alternatives
AttackIQ, Pentera, SafeBreach, XM CyberThree alternatives
AttackIQ Flex, Rapid7 InsightVM, Sophos PhishThreatGPT-6 LunaCymulatePicus Security Validation PlatformChangedAttackIQAttackIQ Flexno first choiceagainst: AttackIQ Flex, Microsoft Defender Attack Simulation Training
Two alternatives
AttackIQ Flex, Picus Security Validation PlatformOne alternative
CymulateFour alternatives
Cymulate, Mandiant Security Validation, Picus Security Validation Platform, SafeBreachTwo alternatives
Atomic Red Team, Infection MonkeyMuse Glimmer 30BCymulateSecureframeChangedno first choiceInfection Monkey, OpenBASno first choiceagainst: AttackIQ, Cymulate, SafeBreach, SafeBreach Validate
Two alternatives
NodeZero, Picus Security Validation PlatformTwo alternatives
Drata, VantaFour alternatives
Atomic Red Team, First Strike, Horizon3.ai NodeZero, MITRE CalderaBold 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 01:52 | yes | 13 | 10 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 01:13 | yes | 4 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 00:40 | yes | 15 | 25 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-05 00:32 | yes | 27 | 2 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 01:10 | yes | 24 | 8 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 23:54 | yes | 5 | 3 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 23:44 | yes | 18 | 26 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 00:36 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:56 | yes | 9 | 35 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 01:00 | yes | 21 | 39 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 01:24 | yes | 21 | 98 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 22:20 | yes | 9 | 19 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-05 01:06 | yes | 3 | 17 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 23:45 | yes | 15 | 18 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 23:25 | no | 0 | 5 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 23:19 | no | 0 | 4 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 01:55 | yes | 18 | 27 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-05 00:57 | yes | 24 | 2 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 22:17 | yes | 24 | 10 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 00:03 | yes | 5 | 3 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 23:48 | yes | 22 | 45 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 23:38 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 00:52 | yes | 5 | 21 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 00:21 | yes | 20 | 31 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 00:00 | yes | 20 | 73 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:06 | yes | 16 | 25 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-04 23:00 | yes | 2 | 15 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 01:29 | yes | 15 | 14 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 23:27 | yes | 9 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 01:29 | yes | 5 | 10 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 23:35 | yes | 21 | 28 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-05 01:08 | yes | 17 | 5 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 22:41 | yes | 21 | 10 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 23:52 | yes | 14 | 9 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 01:36 | yes | 24 | 55 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 23:53 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 22:33 | yes | 10 | 30 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 23:19 | yes | 18 | 28 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 23:56 | yes | 24 | 173 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:51 | yes | 15 | 25 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-05 00:40 | yes | 5 | 26 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 00:36 | yes | 22 | 41 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 23:49 | yes | 9 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 22:21 | yes | 3 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 01:38 | yes | 14 | 22 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-04 23:14 | yes | 18 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:45 | yes | 20 | 9 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 22:55 | yes | 5 | 2 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 00:58 | yes | 20 | 51 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:05 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 00:40 | yes | 9 | 62 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 00:41 | yes | 17 | 24 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 01:24 | yes | 20 | 318 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:45 | yes | 13 | 24 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-05 00:43 | yes | 3 | 12 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 22:13 | yes | 14 | 15 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-05 00:23 | no | 0 | 7 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 00:25 | no | 0 | 8 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 22:48 | yes | 13 | 26 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-05 00:38 | yes | 18 | 4 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:51 | yes | 19 | 10 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 22:59 | no | 0 | 9 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 00:41 | yes | 21 | 62 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:13 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 00:38 | no | 0 | 25 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 23:08 | yes | 20 | 77 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 00:00 | no | 0 | 21 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:05 | no | 0 | 10 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-04 22:37 | yes | 4 | 20 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 00:26 | yes | 14 | 19 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 23:32 | yes | 9 | 8 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 01:31 | yes | 4 | 7 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 01:14 | yes | 23 | 30 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-05 01:01 | yes | 20 | 3 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 22:49 | yes | 22 | 8 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 01:47 | yes | 5 | 4 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 23:38 | yes | 21 | 40 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 23:07 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:31 | yes | 10 | 38 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 01:19 | yes | 21 | 29 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 00:45 | yes | 22 | 51 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 01:16 | yes | 18 | 57 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-05 00:47 | yes | 4 | 16 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 01:10 | yes | 23 | 25 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 NodeZero read as Horizon3.ai NodeZero
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
Picus Security (Picus Validation Platform) read as Picus Security Validation Platform
Unresolved, counted raw
CylancePROTECT
OpenAEV
OpenAEV (formerly OpenBAS) by Filigran
Prelude Security Control Validation
SecureOps
Telos (Attacker Labs)
Tenable Compliance
Discontinued, still offered
No shut-down product was recommended here.