PEO providers for small business buyers
Asked as “PEO”, and as “professional employer organization”, on behalf of a small B2B company. 47 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each. Added to the October 2026 Edition on October 4, 2026; its answers are read by the distilled judge (ai-indexes-judge-qwen3-14b-run3), not the claude-opus-5 judge of the earlier categories: how the two compare.
Standing · first-choice share
70%
JustworksClear leader
70Justworks09TriNet06Rippling15others
70% of first choices, 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.
The standing
Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all fourteen models, for a small B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrant
Show the one product at 0%, ordered by negative rate
Bars are the share of first choices, 0 to 100Every product with at least 10 labels here. Every product name links to its product page.
For buyers
All twenty-one head-to-head pages: the top seven products, each against each
Justworks vs RipplingJustworks vs InsperityJustworks vs PaychexADP TotalSource vs TriNetADP TotalSource vs Paychex PEOADP TotalSource vs RipplingADP TotalSource vs InsperityADP TotalSource vs PaychexTriNet vs Paychex PEOTriNet vs RipplingTriNet vs InsperityTriNet vs PaychexPaychex PEO vs RipplingPaychex PEO vs InsperityPaychex PEO vs PaychexRippling vs InsperityRippling vs PaychexInsperity vs Paychex
One product takes 70% of first choices here, so the chart would put seven markers in one corner and one at the far edge. The two measurements it plots are columns in the standing above: share, and the negative label rate. One product carries a negative rate above 25% in this category.
What they warned about
Five of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Mistral Small, 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.
ADP TotalSource19%
8 of 42 labels negative · 8 of 14 models · 2 hard negative
“ADP is known in the small business community for complex billing structures and bureaucratic customer support” Qwen 3.7 Flash, negative prompt
TriNet15%
7 of 46 labels negative · 6 of 14 models · 1 hard negative
“Cons repeatedly listed are undisclosed pricing and no online quotes... "I absolutely hate TriNet. They are the worst."” Muse Glimmer 30B, negative prompt
Paychex33%
4 of 12 labels negative · 4 of 14 models · 2 hard negative
“Paychex has a mixed-to-negative reputation regarding customer support responsiveness.” Qwen 3.7 Flash, negative prompt
Insperity17%
5 of 29 labels negative · 3 of 14 models · 2 hard negative
“Insperity frequently faces severe backlash on consumer forums and review sites. Common complaints include aggressive collection practices, difficulty canceling contracts” 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
78 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. 1036 links across 183 sites, every framing counted. Ranked by the number of answers carrying the site or page. None of the 252 answers across every segment cited this index's own page for the category.
50 answers · 59 citations · 13 models
vendor site · Deel36 answers · 55 citations · 12 models
33 answers · 35 citations · 12 models
vendor site · FirstHR32 answers · 36 citations · 11 models
29 answers · 29 citations · 10 models
27 answers · 33 citations · 11 models
27 answers · 27 citations · 9 models
vendor site · Rework26 answers · 30 citations · 11 models
24 answers · 32 citations · 12 models
23 answers · 32 citations · 10 models
vendor site · RemotePeople23 answers · 23 citations · 10 models
22 answers · 31 citations · 9 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.
44 answers · 12 models
31 answers · 12 models
29 answers · 11 models
27 answers · 9 models
27 answers · 10 models
24 answers · 10 models
23 answers · 11 models
21 answers · 10 models
20 answers · 9 models
18 answers · 11 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 peo”, “peo”, “peos”. 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 |
|---|---|---|---|---|---|---|---|---|
| Justworks justworks.com | 70% | 282 | 60,500 | 452 | 236,868 | $2,424 | 120 | |
| TriNet trinet.com | 9% | 190 | 74,000 | 909 | 232,419 | $533 | 30 | |
| Rippling rippling.com | 6% | 1260 | 301,000 | 17,886 | 712,399 | $42,013 | 115 | |
| Paychex paychex.com Paychex PEO 4%, Paychex 2% | 6% | 92 | 550,000 | 4,777 | 2,394,396 company | 68 | ||
| ADP parent site ADP TotalSource 2% | 2% | 146 | 2,740,000 | 23,897 | ||||
| Insperity insperity.com | 2% | 98 | 90,500 | 1,172 | 134,574 | $17,835 | 120 | |
| Deel deel.com Deel 2%, Deel PEO 0%, Deel HR 0%, Deel Hire 0% | 2% | 526 | 40,500 | 1,210 | 307,175 | $330,608 | 118 | 5 |
| DecisionHR | 2% | |||||||
| Gusto gusto.com | 0% | 870 | 673,000 | 10,560 | 1,629,483 | 118 | ||
| XcelHR | 0% |
Google's top ten for the three searches hold 21 sites; 1 of them are among the sites the models cited here (deel.com). The first result for “best peo” is trustradius.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 PEO for a small B2B company?”Paraphrase“Which professional employer organization would you recommend to a small business that sells to other businesses?”Comparative“What are the top PEOs for a small team and how do they differ?”Budget-constrained“What is the best PEO for a small company with a tight budget?”Scale-constrained“We are a 30 person company evaluating a PEO. What should we look at?”Negative“Which PEOs should a small business avoid or be cautious about?”
Claude Haiku 4.5no first choiceJustworks, PaychexChangedJustworks, RipplingJustworksno first choiceagainst: ADP TotalSource, Paychex, Rippling
Two alternatives
ADP TotalSource, RipplingFour alternatives
ADP TotalSource, Deel Hire, Insperity, TriNetThree alternatives
Amplify PEO, CoAdvantage, GustoGPT-5.4 miniJustworksTriNetChangedJustworksJustworksagainst: Paychexno first choicenothing named
Five alternatives
ADP TotalSource, Deel, Remote, Rippling, TriNetFive alternatives
ADP TotalSource, Insperity, Justworks, Paychex PEO/Oasis, RipplingFive alternatives
ADP TotalSource, Insperity, Paychex PEO, Rippling, TriNetOne alternative
XcelHRGemini 3.5 FlashRipplingRipplingHeldJustworksJustworksno first choiceagainst: ADP TotalSource, Paychex Oasis, TriNet
Four alternatives
Deel PEO, Insperity, Justworks, TriNetThree alternatives
Justworks, Sequoia One, TriNetFour alternatives
Deel, Insperity, Rippling, TriNetThree alternatives
Gusto, OnPay, RipplingPerplexity SonarJustworksJustworksHeldJustworksJustworksno first choicenothing named
Five alternatives
ADP TotalSource, Deel, Insperity, Multiplier, TriNetTwo alternatives
ADP TotalSource, TriNetFive alternatives
ADP TotalSource, CoAdvantage, Insperity, Rippling, TriNetThree alternatives
Deel, Multiplier, RemoFirstGrok 4.1 FastJustworksJustworksHeldJustworksJustworksagainst: ADP TotalSource, TriNetno first choiceagainst: Tandem HR
Three alternatives
ADP TotalSource, Paychex, TriNetTwo alternatives
Insperity, TriNetFour alternatives
ADP TotalSource, Insperity, Paychex PEO, TriNetOne alternative
DeelMistral SmallJustworksInsperity, JustworksChangedJustworksJustworksno first choicenothing named
Two alternatives
ADP TotalSource, InsperityTwo alternatives
ADP TotalSource, TriNetFive alternatives
ADP TotalSource, CoAdvantage PEO, Insperity, Paychex PEO, TriNetTwo alternatives
Deel HR, FirstHRDeepSeek V4 FlashJustworksagainst: GustoJustworksHeldJustworksagainst: GustoJustworksagainst: ADP TotalSource, G&A Partners, Paychexno first choicenothing named
Three alternatives
ADP TotalSource, Rippling, TriNetThree alternatives
ADP TotalSource, Insperity, TriNetSix alternatives
ADP TotalSource, Deel PEO, Insperity, Remote PEO, Rippling, TriNetOne alternative
Amplify PEOLlama 4 MaverickPaychex PEOno first choiceChangedJustworks, TriNetno first choiceno first choicenothing named
One alternative
InsperityQwen 3.7 FlashRipplingagainst: InsperityJustworksChangedJustworksDecisionHR, Justworks, Paychex PEOagainst: TriNetno first choiceagainst: ADP TotalSource, Insperity, Paychex
Three alternatives
Justworks, Thriple, TriNetTwo alternatives
PeoWorks, TriNetFour alternatives
ADP TotalSource, Paychex Flex, Rippling, TriNetThree alternatives
BBSI, Gusto, OnPayKimi K2JustworksJustworks, TriNetChangedJustworksJustworksno first choiceagainst: ADP TotalSource, Presidion Corporation, TriNet
Three alternatives
ADP TotalSource, Rippling, TriNetTwo alternatives
ADP TotalSource, InsperityThree alternatives
ADP TotalSource, Paychex PEO, TriNetTwo alternatives
Bambee, GustoGLM 4.7 FlashXJustworksJustworks, TriNetChangedJustworks, RipplingJustworksno first choiceagainst: ADP TotalSource, Insperity, TriNet
Three alternatives
ADP TotalSource, Paychex PEO, TriNetOne alternative
InsperityThree alternatives
ADP TotalSource, Paychex, TriNetThree alternatives
Gusto, Paychex PEO, RipplingMiniMax M2.5no first choiceJustworks, TriNetChangedFirstHR, JustworksDeel, Justworksno first choicenothing named
One alternative
GustoThree alternatives
ADP TotalSource, Paychex PEO, XcelHROne alternative
ADP PEO BasicGPT-6 LunaJustworksJustworksHeldJustworksJustworksno first choicenothing named
Two alternatives
Insperity, TriNetOne alternative
TriNetFour alternatives
ADP TotalSource, Insperity, Rippling, TriNetMuse Glimmer 30BADP TotalSource, JustworksJustworksChangedJustworksJustworksagainst: ADP TotalSource, Insperity, TriNetno first choiceagainst: ADP PEO services, Insperity, TriNet
Four alternatives
ADP TotalSource, Insperity, TriNet, XcelHRThree alternatives
Infinity HR, Paychex PEO, 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 | 2026-10-04 21:36 | no | 0 | 4 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 21:27 | yes | 2 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 21:26 | yes | 15 | 26 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-04 21:19 | yes | 20 | 5 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 21:20 | yes | 20 | 13 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 21:28 | yes | 13 | 10 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 21:24 | yes | 21 | 33 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 21:22 | yes | 5 | 4 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 21:42 | no | 0 | 26 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 21:30 | yes | 15 | 23 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 21:36 | yes | 18 | 28 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 21:29 | yes | 5 | 13 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-04 21:38 | yes | 4 | 13 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 21:34 | yes | 16 | 19 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 21:28 | yes | 9 | 7 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 21:20 | yes | 4 | 6 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 21:19 | yes | 10 | 21 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-04 21:35 | yes | 17 | 2 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 21:33 | yes | 22 | 12 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 21:29 | yes | 12 | 9 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 21:31 | yes | 23 | 23 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 21:37 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 21:28 | yes | 8 | 38 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 21:33 | yes | 10 | 12 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 21:41 | yes | 24 | 27 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 21:29 | yes | 5 | 19 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-04 21:34 | yes | 3 | 11 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 21:36 | yes | 21 | 22 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 21:25 | yes | 9 | 9 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 21:41 | yes | 5 | 8 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 21:36 | yes | 21 | 28 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-04 21:22 | yes | 20 | 5 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 21:41 | yes | 21 | 12 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 21:19 | yes | 8 | 9 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 21:20 | yes | 22 | 26 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 21:24 | yes | 5 | 4 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 21:22 | yes | 9 | 34 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 21:41 | yes | 15 | 21 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 21:18 | yes | 18 | 31 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 21:33 | yes | 7 | 19 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-04 21:42 | yes | 7 | 27 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 21:19 | yes | 22 | 28 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 21:29 | yes | 9 | 7 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 21:26 | yes | 3 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 21:35 | yes | 21 | 25 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-04 21:31 | yes | 20 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 21:23 | yes | 19 | 13 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 21:29 | yes | 9 | 7 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 21:30 | yes | 20 | 24 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 21:21 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 21:22 | yes | 9 | 39 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 21:32 | yes | 14 | 40 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 21:20 | yes | 19 | 37 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 21:23 | yes | 12 | 25 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-04 21:39 | yes | 1 | 13 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 21:37 | yes | 10 | 20 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 21:33 | no | 0 | 8 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 21:31 | no | 0 | 6 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 21:28 | yes | 14 | 24 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-04 21:26 | yes | 19 | 6 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 21:37 | yes | 14 | 10 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 21:33 | no | 0 | 9 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 21:25 | yes | 18 | 27 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 21:38 | yes | 5 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 21:31 | yes | 5 | 22 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 21:36 | yes | 15 | 21 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 21:26 | no | 0 | 12 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 21:20 | yes | 5 | 27 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-04 21:23 | yes | 4 | 20 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 21:41 | yes | 13 | 31 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 21:23 | yes | 17 | 10 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 21:19 | yes | 4 | 5 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 21:24 | yes | 29 | 28 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-04 21:37 | yes | 20 | 4 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 21:41 | yes | 21 | 10 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 21:21 | yes | 5 | 7 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 21:42 | yes | 21 | 20 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 21:37 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 21:21 | yes | 23 | 51 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 21:23 | yes | 23 | 56 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 21:26 | yes | 23 | 46 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 21:33 | yes | 19 | 32 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-04 21:23 | yes | 3 | 13 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 21:20 | yes | 24 | 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
ADP read as ADP TotalSource
Unresolved, counted raw
ADP PEO Basic
ADP PEO services
Amplify
CoAdvantage PEO
DecisionHR
Infinity HR
Oasis Payroll
PEO Basic plan by a company
Paychex Oasis
PeoWorks (by ADP)
Presidion Corporation
Remote PEO
Tandem HR
Thriple
Discontinued, still offered
No shut-down product was recommended here.