Ecommerce fraud prevention for enterprise buyers
Asked as “ecommerce fraud prevention platform”, and as “online payment fraud detection tool”, on behalf of an enterprise B2B company. 52 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each. Added to the November 2026 Edition.
Standing · first-choice share
25%
Contested · Sift 13%
25Trustpair13Sift12Signifyd50others
25% of first choices, contested.
Since October 2026▲+1Since October 2026: 24% → 25%, +1 point. Inside the 10-point floor: within noise.Trustpair held the lead, +1 point on 24%, inside the 10-point floor.
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.
Small business
Stripe Radar34%Contested↗new leaderNew leader since October 2026: Stripe Radar (34%) replaces NoFraud (34% then, 14% now), 20 points clear, past the 10-point floor.Standing →Mid-marketStripe Radar15%Contested↗new leaderNew leader since October 2026: Stripe Radar (15%) replaces SEON (16% then, 11% now), 4 points clear, inside the 10-point floor.Standing →Enterprise
Trustpair25%Contested▲+1Since October 2026: 24% → 25%, +1 point. Inside the 10-point floor: within noise.This page
Stripe Radar34%Contested↗new leaderNew leader since October 2026: Stripe Radar (34%) replaces NoFraud (34% then, 14% now), 20 points clear, past the 10-point floor.Standing →Mid-marketStripe Radar15%Contested↗new leaderNew leader since October 2026: Stripe Radar (15%) replaces SEON (16% then, 11% now), 4 points clear, inside the 10-point floor.Standing →EnterpriseTrustpair25%Contested▲+1Since October 2026: 24% → 25%, +1 point. Inside the 10-point floor: within noise.This pageThe 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 rateLabelsQuadrantSince October 2026
01Trustpair25%0%15accepted challenger▲+1Since October 2026: 24% → 25%, +1 point. Inside the 10-point floor: within noise.24% → 25%
Trustpair25%0%15accepted challenger▲+1Since October 2026: 24% → 25%, +1 point. Inside the 10-point floor: within noise.24% → 25%02
Sift13%17%63accepted challenger▲+2Since October 2026: 11% → 13%, +2 points. Inside the 10-point floor: within noise.11% → 13%
Sift13%17%63accepted challenger▲+2Since October 2026: 11% → 13%, +2 points. Inside the 10-point floor: within noise.11% → 13%03
Signifyd12%22%55accepted challenger▼−8Since October 2026: 20% → 12%, −8 points. Inside the 10-point floor: within noise.20% → 12%
Signifyd12%22%55accepted challenger▼−8Since October 2026: 20% → 12%, −8 points. Inside the 10-point floor: within noise.20% → 12%04
Riskified10%22%46accepted challenger▲+3Since October 2026: 7% → 10%, +3 points. Inside the 10-point floor: within noise.7% → 10%
Riskified10%22%46accepted challenger▲+3Since October 2026: 7% → 10%, +3 points. Inside the 10-point floor: within noise.7% → 10%05
SEON6%13%31accepted challenger=heldSince October 2026: 6% → 6%, ±0 points. Inside the 10-point floor: within noise.6% → 6%
SEON6%13%31accepted challenger=heldSince October 2026: 6% → 6%, ±0 points. Inside the 10-point floor: within noise.6% → 6%07
Forter4%26%43criticized challenger=heldSince October 2026: 4% → 4%, ±0 points. Inside the 10-point floor: within noise.4% → 4%
Forter4%26%43criticized challenger=heldSince October 2026: 4% → 4%, ±0 points. Inside the 10-point floor: within noise.4% → 4%08Stripe Radar4%19%16accepted challenger▼−3Since October 2026: 7% → 4%, −3 points. Inside the 10-point floor: within noise.7% → 4%
Stripe Radar4%19%16accepted challenger▼−3Since October 2026: 7% → 4%, −3 points. Inside the 10-point floor: within noise.7% → 4%09
Kount2%18%33accepted challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 10-point floor: within noise.2% → 2%
Kount2%18%33accepted challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 10-point floor: within noise.2% → 2%10
Feedzai2%0%13accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 10-point floor: within noise.0% → 2%
Feedzai2%0%13accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 10-point floor: within noise.0% → 2%11ClearSale2%36%14criticized challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 10-point floor: within noise.0% → 2%
Show the four products at 0%, ordered by negative rate
15
NoFraud0%50%10criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
NoFraud0%50%10criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%14
Fingerprint0%17%12accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
Fingerprint0%17%12accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%13DataDome0%10%10accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
12
Accertify0%0%12accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
Accertify0%0%12accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%The floor is 10 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 can't be told apart from repeat variation, and both are shown. Each index measures its own floor from its own repeat, over its own categories, so the floor differs from one index to the next. Both editions asked the same fourteen models. 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.
For buyers
Head to headHead-to-head pages are published for mid-market buyers, so these open on mid-market figures, not enterprise.
All twenty-eight head-to-head pages: the top eight products, each against each
Stripe Radar vs NoFraudStripe Radar vs ClearSaleStripe Radar vs FingerprintStripe Radar vs ForterSignifyd vs SEONSignifyd vs SiftSignifyd vs NoFraudSignifyd vs ClearSaleSignifyd vs FingerprintSignifyd vs ForterSEON vs SiftSEON vs NoFraudSEON vs ClearSaleSEON vs FingerprintSEON vs ForterSift vs NoFraudSift vs ClearSaleSift vs FingerprintSift vs ForterNoFraud vs ClearSaleNoFraud vs FingerprintNoFraud vs ForterClearSale vs FingerprintClearSale vs ForterFingerprint vs Forter
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 →
0102030405h06
07080910C11
12D13
1415Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Trustpair25%
Trustpair25%02Sift13%
Sift13%03Signifyd12%
Signifyd12%04Riskified10%
Riskified10%05SEON6%
SEON6%06hCaptcha Enterprise6%
07Forter4%
Forter4%08Stripe Radar4%
Stripe Radar4%09Kount2%
Kount2%10Feedzai2%
Feedzai2%11ClearSale2%
12Accertify0%
Accertify0%13DataDome0%
14Fingerprint0%
Fingerprint0%15NoFraud0%
NoFraud0%What they warned about
Three of fourteen models held their first choice under the paraphrase. 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 and GPT-6 Luna 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.
Sift17%
11 of 63 labels negative · 10 of 14 models
“Sift is primarily a fraud and marketing platform, but it has received notable criticism in the enterprise segment for its lack of transparency.” Qwen 3.7 Flash, negative prompt
Signifyd22%
12 of 55 labels negative · 9 of 14 models · 1 hard negative
“Avoid Signifyd and Forter for this specific need—their pricing is opaque” DeepSeek V4 Flash, budget prompt
Riskified22%
10 of 46 labels negative · 8 of 14 models
“Why to be cautious: Riskified offers a "chargeback guarantee," which is attractive, but it comes with high costs and a lack of flexibility.” GLM 4.7 FlashX, negative prompt
Forter26%
11 of 43 labels negative · 7 of 14 models · 1 hard negative
“Avoid Signifyd and Forter for this specific need” DeepSeek V4 Flash, budget prompt
What they cite
Fourteen of the fourteen models returned a source list in this edition: five return the pages they cited and nine the search results they consulted.
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. 1037 links across 259 sites, every framing counted. Ranked by the number of answers carrying the site or page. 1 of the 252 answers across every segment cited this index's own page for the category; the method page measures whether that reading tilts an answer.
vendor site · G241 answers · 91 citations · 12 models
40 answers · 44 citations · 12 models
29 answers · 29 citations · 11 models
vendor site · Fraudio27 answers · 36 citations · 10 models
vendor site · Fraud.net22 answers · 43 citations · 12 models
vendor site · Guideflow22 answers · 22 citations · 11 models
vendor site · Signifyd20 answers · 28 citations · 11 models
vendor site · Sift18 answers · 37 citations · 8 models
vendor site · Trustpair18 answers · 32 citations · 10 models
18 answers · 27 citations · 7 models
vendor site · Accertify18 answers · 22 citations · 10 models
vendor site · Stripe17 answers · 30 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.
40 answers · 12 models
28 answers · 11 models
24 answers · 11 models
19 answers · 10 models
16 answers · 10 models
15 answers · 7 models
13 answers · 8 models
12 answers · 6 models
12 answers · 7 models
11 answers · 7 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 ecommerce fraud prevention platform”, “ecommerce fraud prevention platform”, “ecommerce fraud prevention 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 |
|---|---|---|---|---|---|---|---|---|
| Trustpair trustpair.com | 25% | 22 | 720 | 10 | 13,654 | 2 | ||
| Sift sift.com | 13% | 166 | 27,100 | 5,273 | 16,711 | 2 | 1 | |
| Signifyd signifyd.com | 12% | 195 | 3,600 | 62 | 10,180 | $5,179 | 37 | |
| Riskified riskified.com | 10% | 135 | 2,400 | 80 | 5,111 | 8 | 4 | |
| SEON seon.io | 6% | 124 | 2,900 | 1,709 | 24,522 | 71 | 2 | |
| hCaptcha Enterprise hcaptcha.com | 6% | 16 | 2,204 | 3 | ||||
| Forter forter.com | 4% | 88 | 2,400 | 98 | 1,728 | 7 | ||
| Stripe parent site Stripe Radar 4% | 4% | 109 | 823,000 | 102,741 | ||||
| Fraudio fraudio.com | 4% | 40 | 30 | 0 | 170 | 1 | ||
| Kount kount.com | 2% | 70 | 1,000 | 60 | 3,674 | 0 |
Google's top ten for the three searches hold 27 sites; 3 of them are among the sites the models cited here (fraudio.com, sift.com, stripe.com). The first result for “best ecommerce fraud prevention platform” is sift.com.
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 ecommerce fraud prevention platform for an enterprise B2B company?”Paraphrase“Which online payment fraud detection tool would you recommend to a large B2B company with thousands of employees?”Comparative“What are the top enterprise-grade ecommerce fraud prevention platforms and how do they differ?”Budget-constrained“What is the best ecommerce fraud prevention 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 an ecommerce fraud prevention platform. What should we look at?”Negative“Which ecommerce fraud prevention platforms should a large enterprise avoid or be cautious about?”
Claude Haiku 4.5TrustpairTrustpairHeldRiskified, SignifydSEONagainst: Forter, Kount, Siftno first choiceagainst: ClearSale, Kount, NoFraud, Signifyd
Three alternatives
Accertify, Cybersource, FraudNetThree alternatives
DataVisor, FraudNet, NICE ActimizeFour alternatives
Cybersource, Forter, Kount, SiftOne alternative
FraudLabs ProGPT-5.4 miniForter, RiskifiedSiftChangedno first choiceSignifydno first choiceagainst: Chargeflow, ClearSale, ComplyCube, Fingerprint, NoFraud, SEON, Token of Trust, Wyllo
Three alternatives
Cybersource, Sift, SignifydTwo alternatives
Eftsure, PaymentWorksTwo alternatives
Riskified, SiftGemini 3.5 FlashSiftTrustpairChangedForter, RiskifiedRiskified, Signifydno first choiceagainst: ClearSale, Cybersource Decision Manager, PayPal Fraud Protection, Riskified, Shopify Fraud Filter, Signifyd, Stripe Radar, WooCommerce extensions
Five alternatives
Accertify, Forter, LexisNexis ThreatMetrix, SEON, TreviPayFour alternatives
Accertify, Feedzai, LexisNexis ThreatMetrix, SiftFour alternatives
Kount, SEON, Sift, SignifydFour alternatives
Accertify, Kount, SEON, SiftPerplexity SonarSiftTrustpairChangedagainst: Forter, Riskified, SiftRiskified, SignifydStripe Radaragainst: Forterno first choiceagainst: Fraudio, Kount, NoFraud, SEON, Signifyd, Stripe Radar, cside
Six alternatives
Eftsure, Forter, Signifyd, Trustmi, Trustpair, hCaptcha EnterpriseThree alternatives
Eftsure, Feedzai, TrustmiSix alternatives
Fingerprint, Forter, Kount, SEON, Sift, Stripe RadarTwo alternatives
Riskified, SignifydGrok 4.20SiftTrustpairChangedagainst: PayPal Fraud ProtectionSiftSiftagainst: Forter, Riskified, Signifyd, Stripe Radarno first choiceagainst: Chargeflow, Fingerprint, Forter, Riskified, Sift, Signifyd
Four alternatives
Forter, Riskified, SEON, SignifydFour alternatives
Featurespace, Feedzai, SEON, SiftFour alternatives
Forter, Kount, Riskified, SignifydThree alternatives
Kount, Transmit Security, hCaptcha EnterpriseFour alternatives
Accertify, Forter, Sift, SignifydMistral SmallSumsub, hCaptcha EnterpriseFraudio, TrustpairChangedSiftRiskified, Signifydagainst: Subunono first choiceagainst: Chargeflow, NoFraud, Sift
Three alternatives
Kount, Riskified, SiftTwo alternatives
Feedzai, SiftEight alternatives
Forter, Kount, LexisNexis Risk Solutions, Mastercard Identity Check 360, Riskified, SEON, Signifyd, SumsubTwo alternatives
Forter, Stripe RadarDeepSeek V4 FlashSiftTrustpairChangedRiskified, SignifydSEON, hCaptcha Enterpriseagainst: Forter, Signifydno first choiceagainst: ClearSale, Forter, Kount, Riskified, SEON, Sift, Signifyd
Four alternatives
Forter, Kount, Riskified, SignifydThree alternatives
Eftsure, Feedzai, TrustmiFour alternatives
Accertify, Forter, Kount, SiftTwo alternatives
Fingerprint, RiskifiedLlama 4 MaverickhCaptcha EnterpriseFraudNet, PayPal BraintreeChangedno first choiceSignifydno first choicenothing named
Seven alternatives
Cequence, DataDome, Fingerprint, HUMAN, SEON, Sift, SignifydTwo alternatives
Forter, RiskifiedQwen 3.7 FlashRiskifiedFeedzaiChangedSignifydSignifydagainst: ClearSale, SEON, Siftno first choiceagainst: Forter, Riskified, Sift, Signifyd
Three alternatives
Forter, Sift, SignifydTwo alternatives
Fraudio, SiftSeven alternatives
Adyen RevenueProtect, ClearSale, Forter, Kount, Riskified, SEON, SiftOne alternative
RiskifiedKimi K2SignifydEftsure, TrustpairChangedSignifydKount, SEONno first choiceagainst: Kount, Sift, Signifyd
Three alternatives
Accertify, Forter, KountOne alternative
FeedzaiFive alternatives
Accertify, Forter, Kount, Riskified, SiftOne alternative
SiftGLM 4.7 FlashXTrustpairFraudioChangedRiskified, SignifydClearSale, Riskifiedno first choiceagainst: NoFraud, Riskified, Shopify Native Fraud Filter, Sift, basic Stripe Rules
Two alternatives
Sift, SignifydThree alternatives
Fraud.net, Sift, TrustmiFour alternatives
DataDome, Fraud.net, SEON, SiftTwo alternatives
Sift, SignifydMiniMax M2.5TrustpairTrustpairHeldRiskified, SignifydStripe Radaragainst: DataDomeno first choicenothing named
Three alternatives
Feedzai, Sift, SocureTwo alternatives
Feedzai, FraudNetNine alternatives
ACI Worldwide, ClearSale, Cybersource, DataDome, Feedzai, Forter, Kount, SEON, SiftThree alternatives
ClearSale, Riskified, SignifydGPT-6 LunaForterMedius Fraud & Risk DetectionChangedno first choiceGoogle Cloud Fraud Defense Enterpriseno first choiceagainst: Forter, Kount, Riskified, Sift, Signifyd
Three alternatives
Experian, Riskified, SignifydTwo alternatives
Feedzai, SiftEight alternatives
Adyen Protect, Cybersource Decision Manager, Forter, Kount, Riskified, Sift, Signifyd, Stripe RadarOne alternative
SignifydMuse Glimmer 30BTrustpairTrustpairHeldKount, now Equifax Kount, Sift, SignifydSiftagainst: Forter, Riskified, Signifydno first choiceagainst: Forter, Riskified, Sift, Signifyd
Seven alternatives
DataDome, Forter, Riskified, SEON, Sift, Signifyd, hCaptcha EnterpriseSix alternatives
Eftsure, Feedzai, SEON, Sardine, Sift, TrustmiEight alternatives
Adyen RevenueProtect, DataDome, Fingerprint, Forter, Riskified, SEON, Stripe Radar, hCaptcha EnterpriseOne alternative
hCaptcha EnterpriseBold 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.
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 | 2026-11-01 09:30 | yes | 9 | 7 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:21 | yes | 3 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 12:38 | yes | 10 | 23 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 12:31 | yes | 10 | 4 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:10 | yes | 14 | 36 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 10:00 | yes | 5 | 7 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:56 | yes | 23 | 31 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 09:07 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:59 | yes | 5 | 27 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:42 | yes | 19 | 39 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 10:07 | yes | 20 | 81 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 10:20 | yes | 5 | 27 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:06 | yes | 3 | 16 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:45 | yes | 13 | 17 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 12:49 | yes | 18 | 9 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 11:30 | yes | 3 | 4 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:39 | yes | 9 | 20 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 08:54 | yes | 10 | 3 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:23 | yes | 14 | 28 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:30 | yes | 5 | 6 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 08:47 | yes | 22 | 24 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 08:50 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 12:32 | yes | 5 | 41 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:38 | yes | 19 | 40 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 10:29 | yes | 18 | 16 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 09:57 | yes | 15 | 34 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 09:51 | yes | 2 | 14 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:38 | yes | 13 | 15 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 11:50 | yes | 9 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 11:22 | yes | 7 | 9 s |
| Comparative | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:46 | yes | 11 | 27 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 09:29 | yes | 10 | 8 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:22 | yes | 10 | 34 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:57 | yes | 5 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 12:17 | yes | 24 | 45 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 08:50 | yes | 5 | 3 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 09:54 | yes | 5 | 33 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:27 | yes | 25 | 45 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:56 | yes | 23 | 133 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 12:23 | yes | 15 | 111 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:13 | yes | 8 | 28 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:36 | yes | 19 | 41 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 11:31 | yes | 20 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 11:35 | yes | 5 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 10:43 | yes | 6 | 20 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 10:25 | yes | 10 | 3 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:15 | yes | 22 | 37 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:33 | yes | 5 | 4 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:14 | yes | 23 | 25 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 09:16 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:44 | yes | 10 | 32 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 08:55 | yes | 25 | 75 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 11:53 | yes | 24 | 85 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 12:01 | yes | 21 | 94 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 09:38 | yes | 3 | 15 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:06 | yes | 23 | 33 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 11:29 | yes | 19 | 15 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:48 | yes | 3 | 8 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 10:34 | no | 0 | 17 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 12:21 | yes | 10 | 11 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:10 | yes | 9 | 39 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 08:57 | no | 0 | 7 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:45 | yes | 22 | 32 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 09:52 | yes | 5 | 4 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 10:43 | no | 0 | 33 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:22 | yes | 19 | 52 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:27 | yes | 14 | 24 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 13:00 | no | 0 | 30 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 10:38 | yes | 4 | 21 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:30 | yes | 25 | 27 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:01 | yes | 36 | 15 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 09:05 | yes | 4 | 7 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 11:40 | yes | 9 | 30 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 09:21 | yes | 10 | 5 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:14 | yes | 23 | 36 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:57 | yes | 19 | 12 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 11:45 | yes | 23 | 44 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 10:36 | yes | 5 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 12:25 | yes | 22 | 60 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 11:55 | yes | 25 | 59 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:44 | yes | 24 | 51 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 09:25 | no | 0 | 57 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 09:39 | yes | 3 | 25 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:16 | yes | 24 | 29 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
PayPal read as PayPal Fraud Protection
Stripe read as Stripe Radar
Unresolved, counted raw
Google Cloud Fraud Defense Enterprise
Kount, now Equifax Kount
Mastercard Identity Check 360
Medius Fraud & Risk Detection
RISK IDENT
SAS Fraud
Shopify Native Fraud Filter
Transmit Security
WooCommerce extensions
basic Stripe Rules
Discontinued, still offered
No shut-down product was recommended here.