HR AI Index
September 2026 Edition · The permanent record of this edition. The unqualified address always carries the latest edition.
Index Compensation and total rewards September 2026 Edition

Flexible benefits and lifestyle spending accounts

Asked as “lifestyle spending account platform”, and as “flexible employee benefits platform”, on behalf of a mid-market B2B company. 47 first choices recorded across the direct, paraphrase, budget and scale prompts, twelve models each.
Standing
Contested
30% 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.

01The standing

Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all twelve models, for a mid-market B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrant
01Compt30%0%39accepted challenger
02Forma19%12%42accepted challenger
03Benepass17%7%42accepted challenger
04JOON11%0%10accepted challenger
05Rippling2%8%13accepted challenger
Show the one product at 0%, ordered by negative rate
06Espresa0%10%10accepted challenger
Bars are the share of first choices, 0 to 100Every product with at least 10 labels here. Every product name links to its vendor page.

Recommended versus criticized

Every product with at least 10 labels here, on both axes. The 30% line names a quadrant, not the verdict above: that one needs more than 40%.

Criticized challengerCriticized default
Negative label rate →
01
02
03
04
05
06
Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Compt30%
02Forma19%
03Benepass17%
04JOON11%
05Rippling2%
06Espresa0%

02What they warned about

Zero of twelve models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Gemini 3.5 Flash, Perplexity Sonar, Grok 4.1 Fast, Mistral Small, DeepSeek V4 Flash, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, GLM 4.7 FlashX 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.
Forma
12%
5 of 42 labels negative · 5 of 12 models · 2 hard negative
“Avoid platforms with high implementation fees — Some enterprise-focused providers (like Forma) charge $10,000+ ... overkill” DeepSeek V4 Flash, budget prompt
Benefitfocus
50%
4 of 8 labels negative · 4 of 12 models · 2 hard negative
“reviews frequently describe "worst support ever," constantly rotating account managers, glitches... Multiple reviewers literally say "stay away."−” DeepSeek V4 Flash, negative prompt
Benepass
7%
3 of 42 labels negative · 3 of 12 models · 1 hard negative
“Avoid higher-end ones like Benepass/Forma/Espresa” Grok 4.1 Fast, budget prompt
Ben
33%
2 of 6 labels negative · 2 of 12 models
“both **Thanks Ben (Ben)** and **Benefex** have faced heavy criticism from HR admins for "horrific" or "traumatizing" reporting capabilities” Gemini 3.5 Flash, negative prompt

03What they cite

Citations exist only for the models that return a source list: twelve of the twelve in this edition, and all six flagship models on the expanded tier.

Sites the answers cite

65 of 72 answers in this category came back with a source list, from 12 of 12 models: citations where the model returns them, or the search results it consulted. 6 of those lists are Google grounding redirects that name no site and are left out of the counts. 864 links across 191 sites, every framing counted. Ranked by the number of answers carrying the site or page.

45 answers · 59 citations · 10 models
38 answers · 91 citations · 11 models
vendor site · Guideflow38 answers · 47 citations · 10 models
36 answers · 76 citations · 11 models
vendor site · Compt33 answers · 92 citations · 11 models
vendor site · Kota17 answers · 18 citations · 9 models
11 answers · 12 citations · 7 models
11 answers · 11 citations · 8 models
10 answers · 13 citations · 8 models
10 answers · 10 citations · 8 models
10 answers · 10 citations · 6 models
vendor site · Espresa9 answers · 12 citations · 4 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.

04How 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.
ModelDirect“What is the best lifestyle spending account platform for a mid-market B2B company?”Paraphrase“Which flexible employee benefits platform would you recommend to a mid-sized B2B company?”Comparative“What are the top flexible benefits platforms and how do they differ?”Budget-constrained“What is the best lifestyle spending account platform for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a lifestyle spending account platform. What should we look at?”Negative“Which flexible benefits platforms should I avoid or be cautious about?”
Claude Haiku 4.5Compt
Two alternativesBenepass, Forma
BambooHRChanged
Three alternativesForma, Paycor, Paylocity
Forma
Six alternativesBen, Benefitfocus, Benepass, Benify, Modern Health, Reward Gateway
no first choiceno first choicenothing named
GPT-5.4 miniCompt, Forma
One alternativeThrivePass
Employee NavigatorChanged
Two alternativesEverythingBenefits, Rippling
no first choiceCompt
One alternativeJOON
no first choicenothing named
Gemini 3.5 FlashForma
Three alternativesBenepass, Compt, JOON
BenepassChanged
Three alternativesCompt, Forma, Rippling
Benepass, Compt, Forma
Three alternativesBen, Benefex, Fringe
Compt
Four alternativesFijoya, Holisticly, JOON, PeopleKeep
no first choiceagainst: Ben, Benefex, Employee Benefits Corporation, Forma, Perkbox
Perplexity SonarCompt
Two alternativesBenepass, Forma
FormaChanged
Four alternativesADP Workforce Now, Gusto, Paycor, Rippling
Forma
Seven alternativesBenefex, Benepass, Benify, Compt, Perkbox, Reward Gateway, Zest
against: ADP, BambooHR, Benefitfocus, Gusto, Rippling
JOON
One alternativeCompt
against: Forma
no first choiceagainst: WEX
Grok 4.1 FastForma
Two alternativesBenepass, Compt
against: Guusto
RipplingChanged
Seven alternativesBenepass, Employee Navigator, Forma, Gusto, Justworks, Paycor, PlanSource
Forma
Six alternativesBenepass, Benify, Compt, Espresa, ThrivePass, Zest
Compt
Two alternativesJOON, ThrivePass
against: Benepass, Espresa, Forma, Fringe
Benepass, Compt
One alternativeForma
against: Benefex
Mistral SmallBenepass
Two alternativesCompt, Forma
FormaChanged
Two alternativesJustworks, Kota
Forma
Six alternativesBenepass, Compt, Heka, Perkbox, Rippling, ThrivePass
Compt, JOON
Two alternativesFringe, NHC National HealthClaim
no first choicenothing named
DeepSeek V4 FlashBenepass
Two alternativesCompt, Forma
FormaChanged
Three alternativesPlanSource, Rippling, Zest
Benepass, Forma
Five alternativesBenify, Compt, Espresa, ThrivePass, Zest
against: Gusto
JOON
One alternativeFringe
against: Benepass, Forma
no first choice
Six alternativesBenepass, Compt, Espresa, Forma, PeopleKeep, WEX
against: Benefitfocus, Fidelity, TriNet, TriNet Zenefits, WEX
Llama 4 MaverickBenepass, Compt, Guideflowno first choiceChangedno first choiceComptno first choicenothing named
Qwen 3.7 FlashBenepass, Compt
One alternativeFavorably
NamelyChanged
Two alternativesKota, PlanSource
no first choiceDivvy, Fizz, Ramp
Three alternativesDeel, Nuvio, Remote
against: Workday
no first choiceagainst: Ben, Benepass, HealthKey
Kimi K2Benepass
Two alternativesCompt, Forma
FormaChanged
Four alternativesBambooHR, Gusto, Namely, Rippling
Forma
Six alternativesBen, Benepass, Compt, Happl, Perkbox, Zest
against: Dayforce, Oracle Fusion Cloud HCM, Workday
Compt, JOON
Three alternativesForma, Fringe, Motivosity
no first choiceagainst: Benefitfocus, Eden Health, Forma
GLM 4.7 FlashXCompt, Forma
Three alternativesBenepass, Espresa, ThrivePass
Employee NavigatorChanged
Four alternativesBenepass, CIPHR, Lively, Maxwell Health
no first choiceFringe, JOON
Two alternativesBenepass, Heathade
no first choiceagainst: Benefitfocus, Navia Benefit Solutions, Paylogix, PlanSource, Worksmile, bswift
MiniMax M2.5Benepass
Two alternativesCompt, Forma
FormaChanged
One alternativeBenepass
Forma
Five alternativesADP Workforce Now, Benepass, Compt, Gusto, Rippling
Benafica, Compt
One alternativeForma
no first choicenothing named
Bold is the first choiceAlternatives are counted; the count opens them.What the answer argued against

05The 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
Seventy-two rows: every prompt, every model, every answer.
PromptModelVersion stringTime (UTC)SearchedSourcesLatency
Direct recommendationClaude Haiku 4.5claude-haiku-4-5-202510012026-09-17 18:11yes99 s
Direct recommendationGPT-5.4 minigpt-5.4-mini-2026-03-172026-09-17 20:47yes310 s
Direct recommendationGemini 3.5 Flashgemini-3.5-flash2026-09-17 19:24yes2024 s
Direct recommendationPerplexity Sonarsonar2026-09-17 18:27yes205 s
Direct recommendationGrok 4.1 Fastspacexai/grok-4.1-fast-non-reasoning via vertex2026-09-17 18:33yes3521 s
Direct recommendationMistral Smallmistral/mistral-small via mistral2026-09-17 19:25yes912 s
Direct recommendationDeepSeek V4 Flashdeepseek/deepseek-v4-flash via fireworks2026-09-17 21:13yes2231 s
Direct recommendationLlama 4 Maverickmeta/llama-4-maverick via bedrock2026-09-17 21:01yes52 s
Direct recommendationQwen 3.7 Flashalibaba/qwen3.7-flash via alibaba2026-09-17 20:08yes1032 s
Direct recommendationKimi K2moonshotai/kimi-k2 via novita2026-09-17 21:16yes1123 s
Direct recommendationGLM 4.7 FlashXzai/glm-4.7-flashx via zai2026-09-17 20:44yes1765 s
Direct recommendationMiniMax M2.5minimax/minimax-m2.5 via minimax2026-09-17 18:36yes720 s
ParaphraseClaude Haiku 4.5claude-haiku-4-5-202510012026-09-17 18:40yes158 s
ParaphraseGPT-5.4 minigpt-5.4-mini-2026-03-172026-09-17 18:23yes35 s
ParaphraseGemini 3.5 Flashgemini-3.5-flash2026-09-17 22:04yes1341 s
ParaphrasePerplexity Sonarsonar2026-09-17 21:45yes195 s
ParaphraseGrok 4.1 Fastspacexai/grok-4.1-fast-non-reasoning via vertex2026-09-17 18:51yes4118 s
ParaphraseMistral Smallmistral/mistral-small via mistral2026-09-17 20:46yes54 s
ParaphraseDeepSeek V4 Flashdeepseek/deepseek-v4-flash via fireworks2026-09-17 21:02yes2219 s
ParaphraseLlama 4 Maverickmeta/llama-4-maverick via bedrock2026-09-17 18:49yes54 s
ParaphraseQwen 3.7 Flashalibaba/qwen3.7-flash via alibaba2026-09-17 21:13yes521 s
ParaphraseKimi K2moonshotai/kimi-k2 via novita2026-09-17 19:18yes1021 s
ParaphraseGLM 4.7 FlashXzai/glm-4.7-flashx via zai2026-09-17 21:44yes13130 s
ParaphraseMiniMax M2.5minimax/minimax-m2.5 via minimax2026-09-17 20:55yes1927 s
ComparativeClaude Haiku 4.5claude-haiku-4-5-202510012026-09-17 20:41yes99 s
ComparativeGPT-5.4 minigpt-5.4-mini-2026-03-172026-09-17 18:17yes612 s
ComparativeGemini 3.5 Flashgemini-3.5-flash2026-09-17 21:56yes1453 s
ComparativePerplexity Sonarsonar2026-09-17 18:14yes208 s
ComparativeGrok 4.1 Fastspacexai/grok-4.1-fast-non-reasoning via vertex2026-09-17 21:31yes3917 s
ComparativeMistral Smallmistral/mistral-small via mistral2026-09-17 19:56yes1111 s
ComparativeDeepSeek V4 Flashdeepseek/deepseek-v4-flash via deepinfra2026-09-17 20:21yes2762 s
ComparativeLlama 4 Maverickmeta/llama-4-maverick via bedrock2026-09-17 20:57yes53 s
ComparativeQwen 3.7 Flashalibaba/qwen3.7-flash via alibaba2026-09-17 19:41no035 s
ComparativeKimi K2moonshotai/kimi-k2 via novita2026-09-17 18:54yes1753 s
ComparativeGLM 4.7 FlashXzai/glm-4.7-flashx via zai2026-09-17 19:26yes1369 s
ComparativeMiniMax M2.5minimax/minimax-m2.5 via minimax2026-09-17 18:22yes1533 s
Budget constrainedClaude Haiku 4.5claude-haiku-4-5-202510012026-09-17 18:58no04 s
Budget constrainedGPT-5.4 minigpt-5.4-mini-2026-03-172026-09-17 18:18yes24 s
Budget constrainedGemini 3.5 Flashgemini-3.5-flash2026-09-17 22:07yes2953 s
Budget constrainedPerplexity Sonarsonar2026-09-17 18:34yes207 s
Budget constrainedGrok 4.1 Fastspacexai/grok-4.1-fast-non-reasoning via vertex2026-09-17 19:10yes3820 s
Budget constrainedMistral Smallmistral/mistral-small via mistral2026-09-17 20:43yes109 s
Budget constrainedDeepSeek V4 Flashdeepseek/deepseek-v4-flash via deepinfra2026-09-17 20:23yes1931 s
Budget constrainedLlama 4 Maverickmeta/llama-4-maverick via bedrock2026-09-17 20:37yes52 s
Budget constrainedQwen 3.7 Flashalibaba/qwen3.7-flash via alibaba2026-09-17 19:23no029 s
Budget constrainedKimi K2moonshotai/kimi-k2 via novita2026-09-17 20:04yes1019 s
Budget constrainedGLM 4.7 FlashXzai/glm-4.7-flashx via zai2026-09-17 19:24yes2238 s
Budget constrainedMiniMax M2.5minimax/minimax-m2.5 via minimax2026-09-17 19:08yes1235 s
Scale constrainedClaude Haiku 4.5claude-haiku-4-5-202510012026-09-17 19:27no06 s
Scale constrainedGPT-5.4 minigpt-5.4-mini-2026-03-172026-09-17 20:47no05 s
Scale constrainedGemini 3.5 Flashgemini-3.5-flash2026-09-17 19:39yes1121 s
Scale constrainedPerplexity Sonarsonar2026-09-17 21:36yes208 s
Scale constrainedGrok 4.1 Fastspacexai/grok-4.1-fast-non-reasoning via vertex2026-09-17 18:37yes1111 s
Scale constrainedMistral Smallmistral/mistral-small via mistral2026-09-17 19:29no06 s
Scale constrainedDeepSeek V4 Flashdeepseek/deepseek-v4-flash via fireworks2026-09-17 19:27yes1825 s
Scale constrainedLlama 4 Maverickmeta/llama-4-maverick via bedrock2026-09-17 20:28yes54 s
Scale constrainedQwen 3.7 Flashalibaba/qwen3.7-flash via alibaba2026-09-17 20:47yes934 s
Scale constrainedKimi K2moonshotai/kimi-k2 via novita2026-09-17 19:20yes1375 s
Scale constrainedGLM 4.7 FlashXzai/glm-4.7-flashx via zai2026-09-17 19:55yes10232 s
Scale constrainedMiniMax M2.5minimax/minimax-m2.5 via minimax2026-09-17 21:43yes531 s
Negative framingClaude Haiku 4.5claude-haiku-4-5-202510012026-09-17 18:45yes1811 s
Negative framingGPT-5.4 minigpt-5.4-mini-2026-03-172026-09-17 18:55yes46 s
Negative framingGemini 3.5 Flashgemini-3.5-flash2026-09-17 21:51yes1624 s
Negative framingPerplexity Sonarsonar2026-09-17 20:16yes207 s
Negative framingGrok 4.1 Fastspacexai/grok-4.1-fast-non-reasoning via vertex2026-09-17 20:52yes2415 s
Negative framingMistral Smallmistral/mistral-small via mistral2026-09-17 20:23yes57 s
Negative framingDeepSeek V4 Flashdeepseek/deepseek-v4-flash via fireworks2026-09-17 21:20yes1720 s
Negative framingLlama 4 Maverickmeta/llama-4-maverick via bedrock2026-09-17 20:38yes94 s
Negative framingQwen 3.7 Flashalibaba/qwen3.7-flash via alibaba2026-09-17 20:07yes1359 s
Negative framingKimi K2moonshotai/kimi-k2 via novita2026-09-17 21:02yes2936 s
Negative framingGLM 4.7 FlashXzai/glm-4.7-flashx via zai2026-09-17 18:56yes2923 s
Negative framingMiniMax M2.5minimax/minimax-m2.5 via minimax2026-09-17 21:04no012 s

Normalization in this category

Every judgment call made between the raw labels and the numbers above, listed so it is visible and reversible.

Category-scoped readings
Alight read as Alight Solutions
Navia read as Navia Benefit Solutions
Oracle Cloud HCM read as Oracle Fusion Cloud HCM
Workday HCM read as Workday
Zenefits read as TriNet Zenefits
Unresolved, counted raw
Abound
Benafica
Benello
Darwin
Eden Health
Employee Benefits Corporation (EBC)
Favorably
Fidelity (Workplace/NetBenefits)
Fijoya
Fizz
FlexPath (by SBCBS)
Heathade
Heka
LIVD App
Maxwell Health
NHC National HealthClaim
Nuvio
Discontinued, still offered
No shut-down product was recommended here.
← Earned wage accessPay equity →