Flexible benefits and lifestyle spending accounts for enterprise buyers
Asked as “lifestyle spending account platform”, and as “flexible employee benefits platform”, on behalf of an enterprise B2B company. 47 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
45%
Clear leader
45Forma21Compt15Benepass19others
45% of first choices, clear leader.
Since September 2026↗new leaderNew leader since September 2026: Forma (46%) replaces Compt (38% then, 20% now), 27 points clear, past the 13-point floor.Forma leads at 46%, replacing Compt, which led at 38% and stands at 20% now: 27 points clear, past the floor. The verdict moved from contested to clear leader.
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
Compt37%Contested▼−2Since September 2026: 37% → 34%, −2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketCompt40%Contested▲+5Since September 2026: 30% → 35%, +5 points. Inside the 13-point floor: within noise. Read over the models both editions asked.Standing →Enterprise
Forma45%Clear leader↗new leaderNew leader since September 2026: Forma (46%) replaces Compt (38% then, 20% now), 27 points clear, past the 13-point floor.This page
Compt37%Contested▼−2Since September 2026: 37% → 34%, −2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketCompt40%Contested▲+5Since September 2026: 30% → 35%, +5 points. Inside the 13-point floor: within noise. Read over the models both editions asked.Standing →EnterpriseForma45%Clear leader↗new leaderNew leader since September 2026: Forma (46%) replaces Compt (38% then, 20% now), 27 points clear, past the 13-point floor.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 September 2026
01Forma45%7%58endorsed leader▲+17Since September 2026: 29% → 46%, +17 points. Past the 13-point floor: movement. Read over the models both editions asked.29% → 46%
Forma45%7%58endorsed leader▲+17Since September 2026: 29% → 46%, +17 points. Past the 13-point floor: movement. Read over the models both editions asked.29% → 46%02Compt21%5%37accepted challenger▼−18Since September 2026: 38% → 20%, −18 points. Past the 13-point floor: movement. Read over the models both editions asked.38% → 20%
Compt21%5%37accepted challenger▼−18Since September 2026: 38% → 20%, −18 points. Past the 13-point floor: movement. Read over the models both editions asked.38% → 20%03
Benepass15%4%46accepted challenger▲+4Since September 2026: 11% → 15%, +4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.11% → 15%
Benepass15%4%46accepted challenger▲+4Since September 2026: 11% → 15%, +4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.11% → 15%04
Workday4%18%17accepted challenger▲+3Since September 2026: 2% → 5%, +3 points. Inside the 13-point floor: within noise. Read over the models both editions asked.2% → 5%
Workday4%18%17accepted challenger▲+3Since September 2026: 2% → 5%, +3 points. Inside the 13-point floor: within noise. Read over the models both editions asked.2% → 5%05
Rippling2%27%15criticized challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 2%
Rippling2%27%15criticized challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 2%06
ThrivePass2%29%14criticized challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 2%
ThrivePass2%29%14criticized challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 2%Show the six products at 0%, ordered by negative rate
12
Gusto0%90%10criticized challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 0%
Gusto0%90%10criticized challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 0%11
bswift0%40%10criticized challenger▼−4Since September 2026: 4% → 0%, −4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.4% → 0%
bswift0%40%10criticized challenger▼−4Since September 2026: 4% → 0%, −4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.4% → 0%10
Benefitfocus0%35%20criticized challenger▼−4Since September 2026: 4% → 0%, −4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.4% → 0%
Benefitfocus0%35%20criticized challenger▼−4Since September 2026: 4% → 0%, −4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.4% → 0%09
PlanSource0%20%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 0%
PlanSource0%20%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 0%08
ADP Workforce Now0%16%19accepted challenger▼−4Since September 2026: 4% → 0%, −4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.4% → 0%
ADP Workforce Now0%16%19accepted challenger▼−4Since September 2026: 4% → 0%, −4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.4% → 0%07
Espresa0%0%16accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 0%
Espresa0%0%16accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 0%The floor is 13 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.
Head to head
All twenty-one head-to-head pages: the top seven products, each against each
Compt vs RipplingCompt vs ThrivePassCompt vs FringeBenepass vs FormaBenepass vs JOONBenepass vs RipplingBenepass vs ThrivePassBenepass vs FringeForma vs JOONForma vs RipplingForma vs ThrivePassForma vs FringeJOON vs RipplingJOON vs ThrivePassJOON vs FringeRippling vs ThrivePassRippling vs FringeThrivePass vs Fringe
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 →
010203040506070809101112Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative60%
Key
01Forma45%
Forma45%02Compt21%
Compt21%03Benepass15%
Benepass15%04Workday4%
Workday4%05Rippling2%
Rippling2%06ThrivePass2%
ThrivePass2%07Espresa0%
Espresa0%08ADP Workforce Now0%
ADP Workforce Now0%09PlanSource0%
PlanSource0%10Benefitfocus0%
Benefitfocus0%11bswift0%
bswift0%12Gusto0%
Gusto0%What they warned about
Six of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, Gemini 3.5 Flash, 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.
Gusto90%
9 of 10 labels negative · 8 of 14 models · 7 hard negative
“it lacks advanced features like lifestyle spending accounts, custom benefits categories, or flexible stipend programs, and many companies outgrow Gusto's capabilities” Claude Haiku 4.5, negative prompt
Benefitfocus35%
7 of 20 labels negative · 7 of 14 models · 4 hard negative
“Caution level: High — the most consistently flagged platform in enterprise reviews.... Benefitfocus stands out as the most consistently criticized for large enterprises” DeepSeek V4 Flash, negative prompt
BambooHR100%
5 of 5 labels negative · 5 of 14 models · 4 hard negative
“**Explicitly avoid** for large enterprises... reviewers at scale report it buckles under volume for benefits-only” Grok 4.1 Fast, negative prompt
TriNet Zenefits100%
4 of 4 labels negative · 4 of 14 models · 3 hard negative
“Their benefits modules are often bolt-ons to an HR workflow rather than standalone benefits engines.” Qwen 3.7 Flash, 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
80 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. 1144 links across 234 sites, every framing counted. Ranked by the number of answers carrying the site or page. 26 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.
64 answers · 158 citations · 13 models
51 answers · 72 citations · 13 models
vendor site · Guideflow45 answers · 71 citations · 11 models
vendor site · Compt42 answers · 94 citations · 14 models
vendor site · G240 answers · 75 citations · 14 models
31 answers · 33 citations · 11 models
vendor site · Rippling19 answers · 23 citations · 10 models
vendor site · Espresa17 answers · 29 citations · 11 models
14 answers · 25 citations · 9 models
13 answers · 17 citations · 9 models
vendor site · ADP13 answers · 14 citations · 9 models
vendor site · HiBob13 answers · 13 citations · 8 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.
37 answers · 12 models
30 answers · 12 models
29 answers · 12 models
27 answers · 10 models
26 answers · 12 models
25 answers · 10 models
23 answers · 11 models
17 answers · 9 models
15 answers · 9 models
14 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 lifestyle spending account platform”, “flexible benefits platforms”, “lifestyle spending account platform”. 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 |
|---|---|---|---|---|---|---|---|---|
| Forma forma.ai | 45% | 183 | 49,500 | 43,054 | 6,459 | |||
| Compt compt.io | 21% | 127 | 3,600 | 1,693 | 16,841 | 7 | 2 | |
| Benepass getbenepass.com | 15% | 190 | 14,800 | 99 | 30,964 | 6 | ||
| Workday workday.com | 4% | 383 | 1,220,000 | 23,848 | 2,213,450 | 80 | ||
| Fringe fringe.us | 4% | 36 | 165,000 | 29,782 | 11,516 | 2 | ||
| Benefex | 2% | 170 | 3 | |||||
| Rippling rippling.com | 2% | 1260 | 301,000 | 17,886 | 712,399 | $42,013 | 115 | |
| ThrivePass thrivepass.com | 2% | 50 | 8,100 | 89 | 6,760 | |||
| Alight alight.com Alight Solutions 2% | 2% | 45 | 9,900 | 236 | 530,477 company | $1,663 | 20 | |
| Thryv thryv.com | 2% | 2 |
Google's top ten for the three searches hold 21 sites; 5 of them are among the sites the models cited here (compt.io, espresa.com, g2.com, getbenepass.com, joinforma.com). The first result for “best lifestyle spending account platform” is joinforma.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 lifestyle spending account platform for an enterprise B2B company?”Paraphrase“Which flexible employee benefits platform would you recommend to a large B2B company with thousands of employees?”Comparative“What are the top enterprise-grade flexible benefits platforms and how do they differ?”Budget-constrained“What is the best lifestyle spending account 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 lifestyle spending account platform. What should we look at?”Negative“Which flexible benefits platforms should a large enterprise avoid or be cautious about?”
Claude Haiku 4.5BenepassRippling, WorkdayChangedFormaComptno first choiceagainst: Gusto, Manulife, Paychex Flex, Rippling, Sun Life, TriNet
Four alternatives
Compt, Espresa, Forma, WEX BenefitsThree alternatives
Benefex, Forma, Oracle Fusion Cloud HCMOne alternative
BenefitfocusTwo alternatives
Benepass, FormaGPT-5.4 miniFormaagainst: ThrivePassFormaHeldBenepass, FormaComptno first choiceagainst: BerniePortal, EverythingBenefits, Forma, PayFlex, WEX Benefits
Two alternatives
Benepass, EspresaFour alternatives
Paycom, Rippling, Workday, bswiftTen alternatives
ADP Enterprise HR / Workforce Now, Alight Solutions, Deel, Empyrean Benefits Administration, Personify Health, PlanSource, Remote, Rippling, WEX Benefits, WorkdayTwo alternatives
Espresa, O.C. TannerGemini 3.5 FlashFormaBenefexChangedFormaComptagainst: Benepassno first choiceagainst: Alight Solutions, BambooHR, Benefitfocus, Benepass, Compt, Dayforce, Ease, Employee Navigator, Forma, Gusto, Oracle Cloud HCM Benefits, Rippling, TriNet Zenefits, Workday
Three alternatives
Benepass, Compt, EspresaFour alternatives
Ben, Benepass, Compt, FormaFive alternatives
Ben, Benefex, Benepass, Compt, EspresaOne alternative
FormaPerplexity SonarFormaagainst: ThrivePassFormaHeldFormaFormano first choiceagainst: WEX-style systems
One alternative
BenepassTwo alternatives
ADP Workforce Now, BenepassSix alternatives
ADP Workforce Now, Benefex, Benepass, Darwin, Mercer, WorkdayOne alternative
WEX BenefitsGrok 4.1 FastFormaagainst: ThrivePass, WEX BenefitsFormaHeldno first choiceagainst: ADP Workforce Now, Gusto, RipplingFormaagainst: Compt, JOONno first choiceagainst: BambooHR, Benefitfocus, Benetech, Employee Navigator, Flexible Benefits, Gusto, PlanSource, bswift
Three alternatives
Awardco, Benepass, ComptThree alternatives
Benefitfocus, Benepass, RipplingThree alternatives
Benepass, Fringe, ThrivePassFour alternatives
Benepass, Compt, Forma, ThrivePassMistral SmallFormaFormaHeldBenepassagainst: ZywaveComptno first choiceagainst: BambooHR, Ben, Benefitfocus, Gusto, TriNet Zenefits
Three alternatives
Benepass, Compt, JOONTwo alternatives
ADP Workforce Now, WorkdayFour alternatives
ADP Workforce Now, Alight Solutions, Benefitfocus, ThrivePassThree alternatives
Alegeus, Forma, WEX BenefitsSix alternatives
BenefitHub, Bonusly, Lumen, Motivosity, Wellable, WellhubDeepSeek V4 FlashFormaFormaHeldagainst: Businessolver, bswiftFormaagainst: WorkdayComptagainst: Forma, Motivosityno first choiceagainst: ADP Workforce Now, Benefitfocus, Businessolver, Namely, Perkbox, PlanSource, WEX Benefits, Workday, bswift
Two alternatives
Benepass, ComptTwo alternatives
Benify, ComptFive alternatives
ADP Workforce Now, Benefitfocus, Benepass, Coverflex, RipplingOne alternative
ThrivePassThree alternatives
Benepass, Compt, FormaLlama 4 Maverickno first choiceno first choiceHeldFormaFormaComptagainst: BambooHR, Gusto, TriNet Zenefits
One alternative
BenefexQwen 3.7 FlashBenepassForma, ThrivePassChangedagainst: FlexeBenefitHubThryvno first choiceagainst: BambooHR, Benefitfocus, Gusto, TriNet Zenefits
Three alternatives
Compt, Forma, ThrivePassOne alternative
BenepassThree alternatives
Benepass, Vantage Circle, WorkdayTwo alternatives
Benefitify, UnumKimi K2Benepass, FormaFormaChangedEspresa, Formaagainst: BenevityComptno first choiceagainst: ADP Workforce Now, Gusto, Rippling
Two alternatives
Compt, EspresaFive alternatives
ADP TotalSource, ADP Workforce Now, Alight Solutions, Rippling, bswiftTwo alternatives
Compt, FringeThree alternatives
Benepass, Espresa, FormaFour alternatives
Benepass, Compt, Espresa, FormaGLM 4.7 FlashXFormaFringeChangedBenefitfocusBenepassComptnothing named
Two alternatives
Compt, EspresaFour alternatives
ADP Workforce Now, Benefitfocus, PlanSource, RipplingFive alternatives
ADP Benefits Management, Dayforce, PlanSource, ThrivePass, bswiftTwo alternatives
Espresa, FormaTwo alternatives
Forma, ThrivePassMiniMax M2.5Benepass, Formaagainst: ThrivePassWorkdayChangedWorkdayagainst: SAP SuccessFactorsBenepass, Fringeno first choicenothing named
One alternative
ComptFive alternatives
ADP Vantage HCM, ADP Workforce Now, Benefitfocus, Forma, Oracle Fusion Cloud HCMSix alternatives
ADP Workforce Now, Benefitfocus, Benepass, Dayforce, Oracle Fusion Cloud HCM, PlanSourceTwo alternatives
Espresa, JOONGPT-6 LunaFormaAlight SolutionsChangedBenepass, FormaComptno first choiceagainst: Alight Solutions, Benefitfocus, WEX Benefits, bswift
Two alternatives
Benepass, ComptThree alternatives
Benepass, Businessolver, WorkdayThree alternatives
Benefex, Compt, EspresaOne alternative
FormaMuse Glimmer 30BFormaBenepassChangedBen, FormaComptno first choiceagainst: Benefitfocus, Employee Benefits Corporation, Forma, Gusto, TASC
Two alternatives
Benepass, ComptThree alternatives
ADP Workforce Now, Alight Solutions, FormaTwo alternatives
Benepass, PlanSourceThree alternatives
Benepass, Espresa LSA Plus, FormaBold 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 | 2026-10-01 10:16 | yes | 9 | 7 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 10:06 | yes | 2 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 10:02 | yes | 19 | 25 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-01 10:19 | yes | 15 | 3 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 11:30 | yes | 18 | 19 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 10:47 | yes | 5 | 6 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 11:48 | yes | 19 | 33 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 09:15 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:08 | yes | 7 | 30 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 11:49 | yes | 13 | 20 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 10:51 | yes | 20 | 89 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 07:50 | yes | 13 | 31 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-01 08:12 | yes | 3 | 20 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:05 | yes | 9 | 25 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 09:33 | yes | 17 | 10 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:02 | yes | 4 | 5 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 12:16 | yes | 12 | 52 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-01 09:15 | yes | 19 | 3 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 11:09 | yes | 24 | 18 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 10:41 | yes | 11 | 7 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 10:50 | yes | 22 | 45 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 09:30 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:01 | yes | 25 | 90 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 11:30 | yes | 24 | 27 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 11:52 | yes | 22 | 97 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 10:32 | yes | 5 | 48 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-01 07:53 | yes | 4 | 23 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 09:30 | yes | 22 | 27 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 08:09 | yes | 9 | 9 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 12:00 | yes | 4 | 10 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 07:46 | yes | 22 | 33 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-01 08:43 | yes | 18 | 5 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 09:18 | yes | 22 | 9 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 08:04 | yes | 21 | 14 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 12:01 | yes | 24 | 57 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 10:15 | yes | 5 | 1 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 12:06 | no | 0 | 43 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 08:24 | yes | 25 | 30 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:01 | yes | 21 | 24 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:13 | yes | 14 | 22 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-01 08:14 | yes | 7 | 28 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:08 | yes | 22 | 33 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 12:01 | yes | 17 | 10 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:25 | yes | 2 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:17 | yes | 20 | 28 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-01 09:41 | yes | 16 | 5 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 10:03 | yes | 16 | 11 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 10:01 | yes | 8 | 9 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 08:11 | yes | 21 | 23 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:47 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:16 | no | 0 | 34 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 11:54 | yes | 17 | 24 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 07:51 | yes | 19 | 48 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 10:50 | yes | 13 | 32 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:30 | yes | 2 | 19 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 11:00 | yes | 16 | 30 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 08:50 | yes | 28 | 12 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:47 | yes | 3 | 9 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 12:16 | yes | 10 | 55 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-01 09:45 | yes | 15 | 7 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 11:05 | yes | 17 | 10 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 09:21 | no | 0 | 9 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:58 | yes | 17 | 48 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:41 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 08:30 | yes | 8 | 38 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 09:07 | yes | 18 | 32 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 10:37 | yes | 22 | 75 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 10:54 | no | 0 | 9 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:22 | yes | 5 | 20 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 10:34 | yes | 13 | 28 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 09:24 | yes | 18 | 9 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:12 | yes | 5 | 5 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 07:38 | yes | 18 | 32 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-01 11:40 | yes | 20 | 4 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 11:08 | yes | 22 | 10 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:47 | yes | 5 | 4 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:59 | yes | 23 | 40 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:48 | yes | 5 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:53 | yes | 15 | 75 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 07:50 | yes | 23 | 28 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 07:59 | yes | 21 | 51 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 08:02 | yes | 20 | 31 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-01 09:37 | yes | 5 | 22 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 09:22 | yes | 24 | 32 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
ADP read as ADP Workforce Now
ADP (Vantage / Core) read as ADP Workforce Now
Alight read as Alight Solutions
Ceridian Dayforce read as Dayforce
Oracle Cloud HCM read as Oracle Fusion Cloud HCM
WEX read as WEX Benefits
Workday Benefits read as Workday
Workday HCM read as Workday
Workday HCM (Benefits Module) read as Workday
Zenefits (including TriNet) read as TriNet Zenefits
Unresolved, counted raw
ADP Benefits Management
ADP Enterprise HR / Workforce Now
AdvantageClub AI
Allegis / Trinet (Enterprise Divisions)
Benefitify
Benetech
Cloud Benefits
Darwin (Mercer)
Empyrean Benefits Administration
Enroll
FlexBenefits
Flexe
Lumen
Manulife
Oracle Cloud HCM Benefits
Rippling Flex Benefits
Sun Life
WEX-style systems
Discontinued, still offered
No shut-down product was recommended here.