Global payroll and employer of record
Asked as “employer of record”, and as “global payroll provider”, on behalf of a mid-market B2B company. 54 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
30%
Contested · RemoFirst 20%
30Deel20RemoFirst13Rippling37others
30% of first choices, contested.
Since September 2026▲+5Since September 2026: 22% → 27%, +5 points. Inside the 13-point floor: within noise. Read over the models both editions asked.Deel held the lead, +5 points on 22%, inside the 13-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
Deel33%Contested▲+7Since September 2026: 29% → 36%, +7 points. Inside the 13-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketDeel30%Contested▲+5Since September 2026: 22% → 27%, +5 points. Inside the 13-point floor: within noise. Read over the models both editions asked.This pageEnterprise
G-P23%Contested↗new leaderNew leader since September 2026: G-P (21%) replaces Remote (19% then, 9% now), 13 points clear, inside the 13-point floor.Standing →
Deel33%Contested▲+7Since September 2026: 29% → 36%, +7 points. Inside the 13-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketDeel30%Contested▲+5Since September 2026: 22% → 27%, +5 points. Inside the 13-point floor: within noise. Read over the models both editions asked.This pageEnterpriseG-P23%Contested↗new leaderNew leader since September 2026: G-P (21%) replaces Remote (19% then, 9% now), 13 points clear, inside the 13-point floor.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 September 2026
01Deel30%23%64accepted challenger▲+5Since September 2026: 22% → 27%, +5 points. Inside the 13-point floor: within noise. Read over the models both editions asked.22% → 27%
Deel30%23%64accepted challenger▲+5Since September 2026: 22% → 27%, +5 points. Inside the 13-point floor: within noise. Read over the models both editions asked.22% → 27%02
RemoFirst20%4%26accepted challenger▲+10Since September 2026: 11% → 21%, +10 points. Inside the 13-point floor: within noise. Read over the models both editions asked.11% → 21%
RemoFirst20%4%26accepted challenger▲+10Since September 2026: 11% → 21%, +10 points. Inside the 13-point floor: within noise. Read over the models both editions asked.11% → 21%03
Rippling13%14%43accepted challenger▲+4Since September 2026: 9% → 12%, +4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.9% → 12%
Rippling13%14%43accepted challenger▲+4Since September 2026: 9% → 12%, +4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.9% → 12%04
Papaya Global9%19%42accepted challenger▼−3Since September 2026: 13% → 10%, −3 points. Inside the 13-point floor: within noise. Read over the models both editions asked.13% → 10%
Papaya Global9%19%42accepted challenger▼−3Since September 2026: 13% → 10%, −3 points. Inside the 13-point floor: within noise. Read over the models both editions asked.13% → 10%05
Remote7%23%57accepted challenger=heldSince September 2026: 9% → 8%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.9% → 8%
Remote7%23%57accepted challenger=heldSince September 2026: 9% → 8%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.9% → 8%06
Remote People4%9%11accepted challenger▲+4Since September 2026: 0% → 4%, +4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 4%
Remote People4%9%11accepted challenger▲+4Since September 2026: 0% → 4%, +4 points. Inside the 13-point floor: within noise. Read over the models both editions asked.0% → 4%07
Multiplier2%3%31accepted challenger=heldSince September 2026: 2% → 2%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.2% → 2%
Multiplier2%3%31accepted challenger=heldSince September 2026: 2% → 2%, ±0 points. Inside the 13-point floor: within noise. Read over the models both editions asked.2% → 2%Show the two products at 0%, ordered by negative rate
09G-P0%44%16criticized challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.2% → 0%
G-P0%44%16criticized challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 13-point floor: within noise. Read over the models both editions asked.2% → 0%08
Oyster0%21%33accepted challenger▼−13Since September 2026: 13% → 0%, −13 points. Inside the 13-point floor: within noise. Read over the models both editions asked.13% → 0%
Oyster0%21%33accepted challenger▼−13Since September 2026: 13% → 0%, −13 points. Inside the 13-point floor: within noise. Read over the models both editions asked.13% → 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.
All twenty-one head-to-head pages: the top seven products, each against each
Deel vs RemoteDeel vs Remote PeopleDeel vs MultiplierRemoFirst vs RipplingRemoFirst vs Papaya GlobalRemoFirst vs RemoteRemoFirst vs Remote PeopleRemoFirst vs MultiplierRippling vs Papaya GlobalRippling vs RemoteRippling vs Remote PeopleRippling vs MultiplierPapaya Global vs RemotePapaya Global vs Remote PeoplePapaya Global vs MultiplierRemote vs Remote PeopleRemote vs MultiplierRemote People vs Multiplier
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 →
010203040506070809Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Deel30%
Deel30%02RemoFirst20%
RemoFirst20%03Rippling13%
Rippling13%04Papaya Global9%
Papaya Global9%05Remote7%
Remote7%06Remote People4%
Remote People4%07Multiplier2%
Multiplier2%08Oyster0%
Oyster0%09G-P0%
G-P0%What they warned about
Five of fourteen models held their first choice under the paraphrase. Grok 4.1 Fast, Mistral Small, DeepSeek V4 Flash, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, GLM 4.7 FlashX, MiniMax M2.5 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.
Remote23%
13 of 57 labels negative · 11 of 14 models
“pricing can be high (also around $599 per employee per month) and that support may not be as responsive for smaller businesses” Mistral Small, negative prompt
Deel23%
15 of 64 labels negative · 10 of 14 models · 1 hard negative
“Highest Caution: Active Legal/Ethical Controversies ... Rippling sued Deel alleging corporate espionage” Kimi K2, negative prompt
Papaya Global19%
8 of 42 labels negative · 8 of 14 models · 2 hard negative
“**Papaya Global**: Repeated issues with payroll delays, tax filing errors, and poor support response times in complex markets” Grok 4.1 Fast, negative prompt
G-P44%
7 of 16 labels negative · 7 of 14 models
“written feedback reveals repeated concerns about onboarding, payroll handling, pricing clarity, and support consistency” GLM 4.7 FlashX, 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
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. 1079 links across 213 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 · Deel30 answers · 38 citations · 11 models
vendor site · Remote29 answers · 38 citations · 13 models
vendor site · RemotePeople28 answers · 35 citations · 12 models
26 answers · 39 citations · 12 models
vendor site · Teamed21 answers · 36 citations · 10 models
20 answers · 29 citations · 10 models
vendor site · Rippling20 answers · 29 citations · 12 models
20 answers · 21 citations · 12 models
20 answers · 20 citations · 10 models
vendor site · Pin20 answers · 20 citations · 10 models
vendor site · G219 answers · 21 citations · 9 models
vendor site · Playroll19 answers · 20 citations · 10 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.
22 answers · 12 models
20 answers · 10 models
14 answers · 8 models
12 answers · 8 models
12 answers · 10 models
12 answers · 7 models
11 answers · 7 models
10 answers · 8 models
9 answers · 8 models
9 answers · 9 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 employer of record”, “employer of record”, “eor and global payroll 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 |
|---|---|---|---|---|---|---|---|---|
| Deel deel.com | 30% | 526 | 40,500 | 1,210 | 307,175 | $330,608 | 118 | |
| RemoFirst remofirst.com | 20% | 77 | 1,600 | 21 | 17,414 | $701 | 36 | 1 |
| Rippling rippling.com | 13% | 1260 | 301,000 | 17,886 | 712,399 | $42,013 | 115 | |
| Remote remote.com Remote 7%, Remote People 4% | 11% | 213 | 110,000 | 426,655 | 766,598 | $15,858 | 88 | 3 |
| Papaya papayaglobal.com Papaya Global 9% | 9% | 156 | 246,000 | 31,430 | 189,744 company | $8,309 | 11 | 1 |
| Hire with Columbus hirewithcolumbus.com | 7% | 9 | 50 | 242 | 28 | |||
| Safeguard Global safeguardglobal.com | 4% | 17 | 880 | 39 | 23,341 | $871 | 84 | |
| Multiplier usemultiplier.com | 2% | 69 | 9,900 | 71,234 | 69,887 | $4,584 | 120 | |
| Native Teams nativeteams.com | 2% | 20 | 320 | 86 | 47,722 | $12,206 | 30 | 2 |
| Smart Outsourcing Solution | 2% |
Google's top ten for the three searches hold 23 sites; 3 of them are among the sites the models cited here (remote.com, remotepeople.com, selectsoftwarereviews.com). The first result for “best employer of record” is hrtechedge.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 employer of record for a mid-market B2B company?”Paraphrase“Which global payroll provider would you recommend to a mid-sized B2B company?”Comparative“What are the top EOR and global payroll platforms and how do they differ?”Budget-constrained“What is the best employer of record for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating an employer of record. What should we look at?”Negative“Which EOR and global payroll platforms should I avoid or be cautious about?”
Claude Haiku 4.5DeelDeelHeldRipplingHire with Columbus, RemoFirstno first choiceagainst: Deel, G-P, Oyster, Papaya Global, Remote, Rippling, Skuad
Two alternatives
Multiplier, OysterFour alternatives
Multiplier, Papaya Global, Rippling, RivermateFive alternatives
ADP, Atlas HXM, Deel, Oyster, RemoteOne alternative
MultiplierGPT-5.4 miniDeelDeelHeldagainst: Papaya Globalno first choiceSmart Outsourcing Solutionno first choiceagainst: G-P, Remote, Remote People
Four alternatives
G-P, Multiplier, Oyster, RipplingTwo alternatives
ADP GlobalView Payroll, RemoteOne alternative
MultiplierGemini 3.5 FlashRipplingRipplingHeldDeelHire with Columbus, RemoFirstagainst: Deel, Remote, Ripplingno first choiceagainst: ADP, Deel, G-P, Native Teams, Papaya Global, RemoFirst, Rippling, TriNet
Three alternatives
Deel, Papaya Global, RemoteThree alternatives
Deel, Papaya Global, RemoteFive alternatives
Multiplier, Papaya Global, RemoFirst, Remote, RipplingTwo alternatives
Ontop, PlayrollPerplexity SonarDeelagainst: Papaya GlobalDeelHeldDeel, RemoteRemoFirstno first choicenothing named
Three alternatives
RemoFirst, Remote, RipplingTwo alternatives
Papaya Global, RipplingFive alternatives
G-P, Multiplier, Oyster, Papaya Global, RipplingOne alternative
Native TeamsGrok 4.1 FastDeel, RemoteRipplingChangedDeel, RemoteRemoFirst, Remote Peopleagainst: Deel, Native Teams, Remoteno first choiceagainst: Lano, Papaya Global, Velocity Global, WorkMotion
Three alternatives
Multiplier, RemoFirst, RipplingThree alternatives
Deel, Papaya Global, RemoteSix alternatives
ADP, Dayforce, Multiplier, Omnipresent, Papaya Global, RipplingTwo alternatives
Hire with Columbus, MultiplierMistral SmallDeelPapaya Global, RemoteChangedOmnipresent, RipplingRemoFirstno first choiceagainst: Deel, G-P, Oyster, Paylocity, Remote
Five alternatives
Acvian, Borderless AI, Boundless, Insperity, Safeguard GlobalOne alternative
RivermateFour alternatives
Deel, Oyster, Papaya Global, RemoteOne alternative
MultiplierDeepSeek V4 FlashDeelRipplingChangedagainst: ADPDeelagainst: ADP GlobalView PayrollRemoFirstagainst: Deel, Oyster, Remoteno first choiceagainst: Deel, Papaya Global, Remote
Four alternatives
G-P, Oyster, Remote, RipplingTwo alternatives
Papaya Global, RemoteSeven alternatives
CloudPay, Multiplier, Oyster, Papaya Global, RemoFirst, Remote, RipplingThree alternatives
Native Teams, Remote People, RivermateLlama 4 MaverickSafeguard GlobalPapaya GlobalChangedno first choiceRemoFirstno first choicenothing named
One alternative
DeelTwo alternatives
Deel, RipplingQwen 3.7 FlashDeel, Remote, Safeguard GlobalPapaya GlobalChangedDeelRemoFirst, Remote Peopleagainst: Deel, Remoteno first choiceagainst: Deel, G-P, Remote, Velocity Global
Three alternatives
Remote, Rivermate, UKG ProFive alternatives
Multiplier, Oyster, Papaya Global, Remote, RipplingKimi K2DeelPapaya Global, RipplingChangedagainst: ADPDeelRemoFirstagainst: Deel, Oysterno first choiceagainst: Deel, Oyster, Papaya Global, Remote, Rippling, Velocity Global
Four alternatives
Multiplier, Papaya Global, Remote, RipplingTwo alternatives
Deel, RemoteSeven alternatives
ADP GlobalView Payroll, Oyster, Papaya Global, RemoFirst, Remote, Rippling, Workday PayrollTwo alternatives
Remote People, RivermateGLM 4.7 FlashXDeel, Papaya GlobalRemoteChangedRemoteNative Teamsno first choiceagainst: ADP Employer of Record, G-P, Gloroots, Gusto Employer of Record, Rippling
Four alternatives
Omni HR, Oyster, Remote, RipplingThree alternatives
Deel, Papaya Global, PlayrollTen alternatives
Borderless AI, Deel, G‑P, Multiplier, Oyster, Papaya Global, Playroll, RemoFirst, Remote People, RipplingThree alternatives
Hire with Columbus, RemoFirst, Remote PeopleMiniMax M2.5MultiplierDeel, RipplingChangedDeelHire with Columbus, RemoFirstno first choiceagainst: Deel, Oyster, Remote
Three alternatives
Deel, Papaya Global, RemoteOne alternative
Papaya GlobalEight alternatives
ADP, Multiplier, Oyster, Papaya Global, RemoFirst, Remote, Rippling, Workday PayrollTwo alternatives
Payoneer Workforce Management, PilotGPT-6 LunaDeelDeelHeldno first choiceRemoFirstagainst: Deel, Remoteno first choiceagainst: Deel
Three alternatives
Papaya Global, Remote, RipplingOne alternative
RemoteMuse Glimmer 30BDeelRipplingChangedagainst: ADP Celergo, ADP GlobalView PayrollDeelHire with Columbusno first choiceagainst: ADP Employer of Record, Atlas HXM, Deel, G-P, Multiplier, Oyster, Papaya Global, Remote, Rippling, Skuad, Velocity Global
Two alternatives
Oyster, RemoteTwo alternatives
Deel, PaylocityThree alternatives
ADP GlobalView/Celergo, Oyster, Papaya GlobalOne alternative
RemoFirstBold 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 10:09 | yes | 9 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 10:44 | yes | 6 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:43 | yes | 12 | 23 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-01 11:26 | yes | 19 | 4 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 11:29 | yes | 23 | 9 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 08:07 | yes | 5 | 3 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 07:41 | yes | 23 | 37 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 10:05 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 08:40 | yes | 9 | 32 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 10:09 | yes | 15 | 33 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 11:10 | yes | 11 | 66 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 07:37 | yes | 17 | 68 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:45 | yes | 4 | 16 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 09:50 | yes | 21 | 24 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 11:33 | yes | 18 | 8 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:51 | yes | 3 | 4 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:07 | yes | 10 | 23 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-01 08:48 | yes | 20 | 3 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 07:41 | yes | 22 | 8 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:56 | yes | 5 | 4 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 10:21 | yes | 22 | 26 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 09:59 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 07:44 | yes | 5 | 23 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 11:40 | yes | 19 | 29 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:16 | yes | 14 | 52 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 08:15 | yes | 10 | 20 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:49 | yes | 2 | 15 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 08:34 | yes | 12 | 19 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 10:27 | yes | 9 | 11 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 09:51 | yes | 2 | 7 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:58 | yes | 17 | 24 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-01 08:56 | yes | 19 | 5 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 11:09 | yes | 25 | 10 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 09:59 | yes | 10 | 6 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 08:47 | yes | 25 | 34 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:27 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 11:41 | yes | 10 | 37 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 11:01 | yes | 25 | 38 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 07:47 | yes | 24 | 35 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 07:57 | yes | 15 | 22 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-01 08:35 | yes | 9 | 31 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 10:20 | yes | 15 | 45 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 10:02 | yes | 9 | 7 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 09:37 | yes | 5 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 07:47 | yes | 15 | 19 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-01 10:06 | yes | 23 | 4 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 10:29 | yes | 23 | 8 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:49 | yes | 5 | 3 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:01 | yes | 19 | 30 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 10:48 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:03 | yes | 5 | 21 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 12:06 | yes | 10 | 24 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 09:32 | yes | 19 | 29 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:13 | yes | 15 | 18 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 09:03 | yes | 3 | 11 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 11:37 | yes | 14 | 22 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 07:53 | no | 0 | 6 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:38 | no | 0 | 12 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:25 | yes | 9 | 27 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-01 10:56 | yes | 20 | 5 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 10:35 | yes | 13 | 8 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 09:19 | no | 0 | 6 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 07:53 | yes | 21 | 44 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:23 | yes | 5 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 11:06 | no | 0 | 26 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 11:55 | yes | 24 | 35 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 11:58 | yes | 15 | 98 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:16 | no | 0 | 9 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 07:47 | yes | 1 | 28 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 09:09 | yes | 14 | 26 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 10:43 | yes | 19 | 13 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:52 | yes | 4 | 5 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:07 | yes | 18 | 30 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-01 10:28 | yes | 16 | 3 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 10:59 | yes | 25 | 11 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 09:19 | yes | 5 | 5 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:38 | yes | 25 | 37 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 11:40 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 11:25 | yes | 15 | 77 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 08:03 | yes | 25 | 56 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 10:03 | yes | 24 | 60 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:50 | yes | 24 | 39 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:26 | yes | 1 | 53 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 07:50 | yes | 25 | 49 s |
Noise floor in this category
Flips between the edition run and its calibration repeat. Six prompts per model is a small sample; the index-wide floor is the number to trust.
ShowHide
Claude Haiku 4.5
4 of 4 flipped
GPT-5.4 mini
2 of 3 flipped
Gemini 3.5 Flash
3 of 4 flipped
Perplexity Sonar
1 of 4 flipped
Grok 4.1 Fast
3 of 4 flipped
Mistral Small
4 of 4 flipped
DeepSeek V4 Flash
3 of 5 flipped
Llama 4 Maverick
0 of 3 flipped
Qwen 3.7 Flash
4 of 5 flipped
Kimi K2
4 of 5 flipped
GLM 4.7 FlashX
4 of 4 flipped
MiniMax M2.5
3 of 4 flipped
GPT-6 Luna
0 of 3 flipped
Muse Glimmer 30B
3 of 4 flipped
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 Global Payroll read as ADP GlobalView Payroll
ADP GlobalView read as ADP GlobalView Payroll
Atlas read as Atlas HXM
Ceridian (Dayforce) read as Dayforce
Oracle read as Oracle HCM Cloud
Oyster HR read as Oyster
Papaya read as Papaya Global
Paychex read as Paychex Flex
Paylocity Global Payroll read as Paylocity
RemotePeople read as Remote People
SAP read as SAP SuccessFactors Employee Central Payroll
TopSource Worldwide read as TopSource
Workday read as Workday Payroll
Unresolved, counted raw
Acvian
Ambacia
Blue Marble
Gusto Employer of Record
G‑P (Globalization Partners)
G‑P (Global‑People)
Safeguard
Smart Outsourcing Solution
Thera
Discontinued, still offered
No shut-down product was recommended here.