Multi-factor authentication
Asked as “MFA solution”, and as “multi-factor authentication tool”, on behalf of a mid-market B2B company. 65 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
43%
Clear leader
43Cisco Duo29Microsoft Entra ID08Okta Verify20others
43% of first choices, clear leader.
Since October 2026▼−4Since October 2026: 47% → 43%, −4 points. Inside the 11-point floor: within noise.Cisco Duo held the lead, −4 points on 47%, inside the 11-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
Cisco Duo37%Contested▼−3Since October 2026: 40% → 37%, −3 points. Inside the 11-point floor: within noise.Standing →Mid-marketCisco Duo43%Clear leader▼−4Since October 2026: 47% → 43%, −4 points. Inside the 11-point floor: within noise.This pageEnterprise
Microsoft Entra ID54%Clear leader▲+13Since October 2026: 41% → 54%, +13 points. Past the 11-point floor: movement.Standing →
Cisco Duo37%Contested▼−3Since October 2026: 40% → 37%, −3 points. Inside the 11-point floor: within noise.Standing →Mid-marketCisco Duo43%Clear leader▼−4Since October 2026: 47% → 43%, −4 points. Inside the 11-point floor: within noise.This pageEnterpriseMicrosoft Entra ID54%Clear leader▲+13Since October 2026: 41% → 54%, +13 points. Past the 11-point floor: movement.Standing →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 October 2026
01Cisco Duo43%2%66endorsed leader▼−4Since October 2026: 47% → 43%, −4 points. Inside the 11-point floor: within noise.47% → 43%
Cisco Duo43%2%66endorsed leader▼−4Since October 2026: 47% → 43%, −4 points. Inside the 11-point floor: within noise.47% → 43%02Microsoft Entra ID29%0%56accepted challenger▼−1Since October 2026: 30% → 29%, −1 point. Inside the 11-point floor: within noise.30% → 29%
Microsoft Entra ID29%0%56accepted challenger▼−1Since October 2026: 30% → 29%, −1 point. Inside the 11-point floor: within noise.30% → 29%03
Okta Verify8%13%53accepted challenger▼−5Since October 2026: 13% → 8%, −5 points. Inside the 11-point floor: within noise.13% → 8%
Okta Verify8%13%53accepted challenger▼−5Since October 2026: 13% → 8%, −5 points. Inside the 11-point floor: within noise.13% → 8%04
Google Authenticator Lab in the set6%44%32criticized challenger▲+6Since October 2026: 0% → 6%, +6 points. Inside the 11-point floor: within noise.0% → 6%
Google Authenticator Lab in the set6%44%32criticized challenger▲+6Since October 2026: 0% → 6%, +6 points. Inside the 11-point floor: within noise.0% → 6%05
Microsoft Authenticator5%28%18criticized challenger▲+3Since October 2026: 2% → 5%, +3 points. Inside the 11-point floor: within noise.2% → 5%
Microsoft Authenticator5%28%18criticized challenger▲+3Since October 2026: 2% → 5%, +3 points. Inside the 11-point floor: within noise.2% → 5%06
Authy2%31%13criticized challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise.0% → 2%
Authy2%31%13criticized challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise.0% → 2%Show the five products at 0%, ordered by negative rate
10
Ping Identity0%8%12accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Ping Identity0%8%12accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%07
YubiKey0%5%21accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
YubiKey0%5%21accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%08
Auth00%0%19accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Auth00%0%19accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%09
JumpCloud Protect0%0%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
JumpCloud Protect0%0%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%11
OneLogin MFA0%0%11accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise.2% → 0%
OneLogin MFA0%0%11accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise.2% → 0%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 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.
Google Authenticator is made by Google, whose model Gemini 3.5 Flash is in the set. On the four share prompts that model made it the first choice zero times of 4; the other thirteen models four times of 52. Lab treatment is defined on the method page; the row is marked, not excluded.
Head to head
All fifteen head-to-head pages: the top six products, each against each
Cisco Duo vs Microsoft AuthenticatorCisco Duo vs AuthyMicrosoft Entra ID vs Okta VerifyMicrosoft Entra ID vs Google AuthenticatorMicrosoft Entra ID vs Microsoft AuthenticatorMicrosoft Entra ID vs AuthyOkta Verify vs Google AuthenticatorOkta Verify vs Microsoft AuthenticatorOkta Verify vs AuthyGoogle Authenticator vs Microsoft AuthenticatorGoogle Authenticator vs AuthyMicrosoft Authenticator vs Authy
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 →
0102030405060708091011Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative60%
Key
01Cisco Duo43%
Cisco Duo43%02Microsoft Entra ID29%
Microsoft Entra ID29%03Okta Verify8%
Okta Verify8%04Google Authenticator6%
Google Authenticator6%05Microsoft Authenticator5%
Microsoft Authenticator5%06Authy2%
Authy2%07YubiKey0%
YubiKey0%08Auth00%
Auth00%09JumpCloud Protect0%
JumpCloud Protect0%10Ping Identity0%
Ping Identity0%11OneLogin MFA0%
OneLogin MFA0%What they warned about
Nine of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Grok 4.20, Qwen 3.7 Flash and MiniMax M2.5 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.
Google Authenticator44%
14 of 32 labels negative · 8 of 14 models · 2 hard negative
“Avoid for mid-size: Pure consumer tools like Google Authenticator (too basic, no central management)” Grok 4.20, paraphrase prompt
Authy31%
4 of 13 labels negative · 4 of 14 models
“TOTP authenticator apps – e.g., Google Authenticator, Authy. They are stronger than SMS/email, but the 6-digit codes can be phished in real time” Muse Glimmer 30B, negative prompt
Microsoft Authenticator28%
5 of 18 labels negative · 4 of 14 models
“Cybercriminals exploit push-based MFA apps (like Microsoft Authenticator) by bombarding users with authentication requests until they accidentally approve one” Claude Haiku 4.5, negative prompt
Okta Verify13%
7 of 53 labels negative · 3 of 14 models · 1 hard negative
“Avoid premium-heavy tools like Okta (can get expensive)” Grok 4.20, 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
67 of 84 answers in this category came back with a source list, from 13 of 14 models: citations where the model returns them, or the search results it consulted. 656 links across 168 sites, every framing counted. Ranked by the number of answers carrying the site or page. The other 1 model searched through a gateway that returned no source list on this edition. 20 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.
34 answers · 34 citations · 10 models
30 answers · 33 citations · 11 models
vendor site · CISA25 answers · 53 citations · 12 models
25 answers · 39 citations · 10 models
vendor site · MojoAuth18 answers · 24 citations · 8 models
vendor site · OneLogin17 answers · 20 citations · 8 models
vendor site · Okta16 answers · 25 citations · 10 models
16 answers · 16 citations · 9 models
vendor site · Protectimus15 answers · 15 citations · 9 models
vendor site · G214 answers · 17 citations · 9 models
14 answers · 14 citations · 7 models
vendor site · Microsoft13 answers · 16 citations · 5 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.
34 answers · 10 models
28 answers · 11 models
16 answers · 9 models
16 answers · 8 models
15 answers · 9 models
14 answers · 7 models
12 answers · 8 models
12 answers · 6 models
11 answers · 7 models
9 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 mfa solution”, “mfa solution”, “mfa solutions”. 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 |
|---|---|---|---|---|---|---|---|---|
| Cisco parent site Cisco Duo 43% | 43% | 189 | 165,000 | 48,352 | ||||
| Microsoft parent site Microsoft Entra ID 29%, Microsoft Authenticator 5%, Microsoft 365 2% | 35% | 499 | 2,240,000 | 403,136 | ||||
| Okta Verify okta.com | 8% | 122 | 49,500 | 1,322 | 1,959,740 | 118 | ||
| Google Titan google.dev Google Authenticator 6%, Google Titan 0% | 6% | 60 | 165,000 | 2,858 | 881,346 | 109 | ||
| Google Workspace workspace.google.com Google Workspace 2-Step Verification 5% | 5% | 17 | 368,000 | 7,422 | 40,583,075 | $2,344 | ||
| Authy authy.com | 2% | 16 | 9,900 | 435 | 13,979 | |||
| Microsoft Entra Security Defaults | 2% | |||||||
| YubiKey yubico.com | 0% | 53 | 49,500 | 2,536 | 97,363 | 32 | ||
| Auth0 auth0.com | 0% | 245 | 18,100 | 772 | 170,673 | 117 | ||
| JumpCloud Protect jumpcloud.com | 0% | 32 | 170 | 6 | 108,479 | $8,612 | 80 | 7 |
Google's top ten for the three searches hold 24 sites; 3 of them are among the sites the models cited here (aimultiple.com, microsoft.com, onelogin.com). The first result for “best mfa solution” is miniorange.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 MFA solution for a mid-market B2B company?”Paraphrase“Which multi-factor authentication tool would you recommend to a mid-sized B2B company?”Comparative“What are the top MFA solutions and how do they differ?”Budget-constrained“What is the best MFA solution for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a MFA solution. What should we look at?”Negative“Which MFA solutions should I avoid or be cautious about?”
Claude Haiku 4.5Cisco DuoOkta VerifyChangedno first choiceAuthy, Google Authenticator, Microsoft Authenticatorno first choiceagainst: Microsoft Authenticator
Three alternatives
JumpCloud Protect, Microsoft Entra ID, Okta VerifyTwo alternatives
Cisco Duo, Microsoft Authenticator or Azure AD/Entra IDTen alternatives
Auth0, Cisco Duo, Google Authenticator, HYPR, Keycloak, LastPass MFA, Microsoft Entra ID, MojoAuth, Okta Verify, Ping IdentitySix alternatives
AWS IAM, Cisco Duo, Google Workspace 2-Step Verification, LastPass MFA, Microsoft Entra ID, Okta VerifyGPT-5.4 miniMicrosoft Entra ID, Okta VerifyCisco DuoChangedMicrosoft Entra IDGoogle Workspace 2-Step Verification, Microsoft Entra IDagainst: Authyno first choiceagainst: Email OTPs, One-time codes entered manually from authenticator apps, Push approvals without number matching / context, SMS text codes, Voice-call codes
Two alternatives
Microsoft Entra ID, Okta VerifyFour alternatives
Cisco Duo, Okta Verify, Ping Identity, PingIDFour alternatives
Duo MFA, Duo Mobile, Google Authenticator, Microsoft AuthenticatorGemini 3.5 FlashCisco DuoCisco DuoHeldCisco Duo, Microsoft Entra IDGoogle Workspace 2-Step Verification, Microsoft 365, Microsoft Entra IDagainst: YubiKeyMicrosoft Entra IDagainst: 1Password, Authy, Google Authenticator, Microsoft Authenticator
Five alternatives
Auth0, JumpCloud Protect, Microsoft Entra ID, Okta Verify, WorkOSSeven alternatives
Auth0, Clerk, Descope, JumpCloud Protect, Microsoft Entra ID, Okta Verify, StytchThree alternatives
Okta Verify, Ping Identity, YubiKeyFour alternatives
Authelia, Authentik, Cisco Duo, JumpCloud ProtectThree alternatives
Cisco Duo, Okta Verify, Ping IdentityPerplexity SonarCisco DuoCisco DuoHeldMicrosoft Entra IDCisco Duo, Microsoft Entra IDno first choicenothing named
Three alternatives
JumpCloud Protect, Microsoft Entra ID, Okta VerifySix alternatives
Auth0, Descope, Microsoft Entra ID, Okta Verify, Stytch, WorkOS AuthKitSeven alternatives
Auth0 MFA, Cisco Duo, Datawiza, Google Authenticator, Okta Verify, RSA SecurID, YubiKeyOne alternative
miniOrangeGrok 4.20Cisco Duo, Microsoft Entra IDagainst: 1Password, Google Authenticator, Keeper, Okta VerifyCisco DuoChangedagainst: Google Authenticator, Ping Identity, RSA SecurIDMicrosoft Entra ID, Okta Verifyagainst: Google AuthenticatorMicrosoft Entra IDagainst: Okta Verify, PingIDno first choiceagainst: Cisco Duo, Okta Verify
Two alternatives
Microsoft Entra ID, Okta VerifyFour alternatives
Auth0, Cisco Duo, OneLogin MFA, Ping IdentityFour alternatives
Auth0, Cisco Duo, Google Authenticator or Google Workspace MFA, JumpCloud ProtectMistral SmallCisco Duo, Microsoft Entra IDCisco Duo, Microsoft Entra IDHeldno first choiceMicrosoft Authenticatoragainst: Google Authenticatorno first choicenothing named
Two alternatives
Okta Verify, OneLogin MFATwo alternatives
Cisco Duo, OTPLESSDeepSeek V4 FlashCisco Duoagainst: Okta VerifyCisco DuoHeldagainst: Okta Verifyno first choiceCisco Duo, Microsoft Entra IDCisco Duo, Microsoft Entra ID, Okta Verifyagainst: Authy, Duo Push, Google Authenticator, Microsoft Authenticator, Okta Verify
Two alternatives
Auth0, Microsoft Entra IDOne alternative
Microsoft Entra IDSix alternatives
Auth0, Cisco Duo, Microsoft Entra ID, Okta Verify, Ping Identity, RSA SecurIDThree alternatives
Google Authenticator, ManageEngine ADSelfService Plus, Microsoft AuthenticatorLlama 4 MaverickCisco DuoCisco DuoHeldno first choiceCisco Duo, Google Authenticatorno first choicenothing named
Two alternatives
Microsoft Entra ID, Okta VerifyTwo alternatives
Microsoft Entra ID, Okta VerifyQwen 3.7 FlashMicrosoft Entra ID, Okta VerifyMicrosoft Entra IDChangedCisco Duo, Microsoft Entra IDagainst: Google Authenticator, MS AuthenticatorCisco Duono first choiceagainst: Email-Based Codes, Google Authenticator, Push Notifications, SMS Text Messages
Two alternatives
Cisco Duo, JumpCloud ProtectTwo alternatives
Auth0, Cisco DuoFive alternatives
Auth0, ManageEngine ADSelfService+, Okta Verify, OneLogin MFA, Ping IdentityFour alternatives
Authy, Google Workspace 2-Step Verification, Microsoft Authenticator, Microsoft Entra IDFour alternatives
Cisco Duo, Google Identity, Microsoft Entra ID, Okta VerifyKimi K2Cisco DuoCisco DuoHeldOkta Verifyagainst: Google Authenticator, Microsoft AuthenticatorMicrosoft Entra IDagainst: Google Authenticator, Microsoft AuthenticatorMicrosoft Entra IDagainst: Google Authenticator
Two alternatives
Microsoft Entra ID, Okta VerifyFour alternatives
Auth0, Microsoft Entra ID, Okta Verify, PingIDFour alternatives
Auth0, Cisco Duo, Microsoft Entra ID, Ping IdentityOne alternative
Cisco DuoThree alternatives
Cisco Duo, JumpCloud Protect, Okta VerifyGLM 4.7 FlashXCisco Duoagainst: Okta VerifyCisco DuoHeldOkta Verifyagainst: Google AuthenticatorCisco Duo, Microsoft Entra IDCisco Duoagainst: Google Authenticator
One alternative
Microsoft Entra IDOne alternative
Microsoft Entra IDEight alternatives
Auth0, Cisco Duo, FusionAuth, JumpCloud Protect, Microsoft Entra ID, OneLogin MFA, PingID, Thales SafeNet Trusted AccessFour alternatives
Auth0, Google Authenticator, Microsoft Authenticator, Okta VerifyThree alternatives
Microsoft Entra ID, Okta Verify, OneLogin MFAMiniMax M2.5Cisco DuoMicrosoft Entra ID, Okta VerifyChangedMicrosoft Entra IDGoogle Authenticatorno first choicenothing named
One alternative
Microsoft Entra IDThree alternatives
Cisco Duo, Google Workspace 2-Step Verification, JumpCloud ProtectNine alternatives
1Password, Auth0, Cisco Duo, Google Authenticator, Keeper Security, LastPass MFA, Okta Verify, Silverfort, YubiKeyFour alternatives
1Password, Cisco Duo, JumpCloud Protect, LastPass MFAGPT-6 LunaMicrosoft Entra IDMicrosoft Entra IDHeldMicrosoft Entra IDGoogle Workspace 2-Step Verification, Microsoft Entra Security Defaultsno first choicenothing named
Two alternatives
Cisco Duo, Okta VerifyOne alternative
Cisco DuoFive alternatives
Cisco Duo, Google Cloud Identity, Google Workspace 2-Step Verification, Okta Verify, Ping IdentityOne alternative
Cisco DuoMuse Glimmer 30BCisco DuoCisco DuoHeldno first choiceGoogle Authenticator, Microsoft Authenticatorno first choiceagainst: Authy, Google Authenticator
Two alternatives
Microsoft Entra ID, Okta VerifyOne alternative
Microsoft Entra IDTwo alternatives
Cisco Duo, Microsoft Entra IDBold 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 14:46 | yes | 16 | 10 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 09:44 | yes | 2 | 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 12:31 | no | 0 | 19 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 10:54 | yes | 10 | 4 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 16:24 | yes | 9 | 12 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 08:49 | yes | 5 | 5 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 13:24 | yes | 22 | 22 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 14:36 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:38 | no | 0 | 29 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:20 | yes | 10 | 41 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 15:29 | yes | 19 | 101 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 18:20 | yes | 5 | 20 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 14:27 | yes | 4 | 14 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 15:52 | yes | 13 | 18 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 17:42 | no | 0 | 5 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:51 | yes | 4 | 5 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 10:28 | no | 0 | 17 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 10:05 | yes | 10 | 3 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 16:28 | yes | 5 | 8 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 16:38 | yes | 5 | 5 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 16:38 | yes | 12 | 26 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 09:12 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 18:53 | no | 0 | 25 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 13:04 | yes | 5 | 18 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 18:28 | yes | 10 | 27 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:47 | no | 0 | 11 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 17:47 | yes | 3 | 18 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 16:58 | yes | 13 | 17 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:40 | yes | 9 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 18:27 | yes | 8 | 12 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 13:23 | no | 0 | 18 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 08:45 | yes | 10 | 7 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 16:27 | yes | 5 | 19 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:26 | yes | 5 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 14:01 | yes | 22 | 60 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 12:24 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 09:16 | yes | 9 | 48 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 08:42 | yes | 13 | 31 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 15:56 | yes | 15 | 55 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 14:44 | yes | 5 | 84 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 13:24 | yes | 6 | 18 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 19:03 | yes | 13 | 25 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:51 | no | 0 | 5 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 15:49 | no | 0 | 3 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 15:49 | no | 0 | 13 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 12:52 | yes | 10 | 4 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 18:55 | yes | 5 | 12 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 15:20 | yes | 5 | 5 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 11:19 | yes | 24 | 18 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 13:07 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:57 | yes | 5 | 34 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:34 | yes | 10 | 24 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 19:16 | yes | 13 | 28 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:10 | yes | 5 | 23 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:56 | yes | 3 | 8 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 16:24 | yes | 11 | 18 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 12:04 | no | 0 | 6 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 14:43 | no | 0 | 7 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 09:58 | no | 0 | 14 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 09:43 | yes | 10 | 7 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 17:11 | yes | 10 | 12 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 13:28 | no | 0 | 6 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 11:02 | yes | 19 | 37 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 19:13 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 17:17 | no | 0 | 30 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 17:41 | yes | 24 | 43 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 13:39 | yes | 15 | 31 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 16:28 | yes | 5 | 22 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 12:45 | yes | 4 | 18 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 18:31 | no | 0 | 2 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:19 | yes | 18 | 10 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 18:46 | yes | 5 | 6 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 19:34 | no | 0 | 13 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 10:58 | yes | 10 | 4 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 19:25 | yes | 9 | 11 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 09:54 | yes | 5 | 5 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:21 | yes | 21 | 24 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 16:15 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 18:20 | yes | 8 | 41 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 15:23 | yes | 13 | 57 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 11:04 | yes | 21 | 38 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:22 | yes | 10 | 128 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 18:35 | yes | 5 | 11 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 11:04 | yes | 21 | 28 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
Google Workspace read as Google Workspace 2-Step Verification
Google Workspace (G-Suite) read as Google Workspace 2-Step Verification
Google's built-in 2-Step Verification read as Google Workspace 2-Step Verification
JumpCloud read as JumpCloud Protect
LastPass read as LastPass MFA
Microsoft Entra ID Conditional Access read as Microsoft Entra ID
Okta read as Okta Verify
Okta Adaptive MFA read as Okta Verify
Okta Adaptive MFA (Workforce Identity Cloud) read as Okta Verify
Okta Adaptive MFA (including Auth0) read as Okta Verify
Okta Identity Cloud read as Okta Verify
Okta MFA read as Okta Verify
Okta Workforce Identity read as Okta Verify
Okta Workforce Identity Cloud read as Okta Verify
Okta Workforce Identity Cloud (Essentials) read as Okta Verify
OneLogin read as OneLogin MFA
OneLogin by One Identity read as OneLogin MFA
Thales read as Thales SafeNet Trusted Access
Unresolved, counted raw
1Password Passkeys
2FAS
Email OTPs
Email-Based Codes
Google Identity
Google Titan Security Key
MS Authenticator
ManageEngine ADSelfService+
Microsoft Authenticator or Azure AD/Entra ID
Microsoft Entra Security Defaults
One Identity Defender
One-time codes entered manually from authenticator apps
Push Notifications
Push approvals without number matching / context
SMS Text Messages
SMS text codes
Titan Key
Titan Keys
Verify Now
Voice-call codes
Discontinued, still offered
No shut-down product was recommended here.