PEO providers for small business buyers
Asked as “PEO”, and as “professional employer organization”, on behalf of a small B2B company. 45 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each. Added to the November 2026 Edition.
Standing · first-choice share
76%
Clear leader
76Justworks09Rippling07ADP TotalSource09others
76% of first choices, clear leader.
Since October 2026▲+6Since October 2026: 70% → 76%, +6 points. Inside the 13-point floor: within noise.Justworks held the lead, +6 points on 70%, 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
Justworks76%Clear leader▲+6Since October 2026: 70% → 76%, +6 points. Inside the 13-point floor: within noise.This pageMid-market
ADP TotalSource37%Contested↗new leaderNew leader since October 2026: ADP TotalSource (37%) replaces Justworks (24% then, 28% now), 9 points clear, inside the 13-point floor.Standing →EnterpriseADP TotalSource67%Clear leader▲+5Since October 2026: 62% → 67%, +5 points. Inside the 13-point floor: within noise.Standing →
Justworks76%Clear leader▲+6Since October 2026: 70% → 76%, +6 points. Inside the 13-point floor: within noise.This pageMid-marketADP TotalSource37%Contested↗new leaderNew leader since October 2026: ADP TotalSource (37%) replaces Justworks (24% then, 28% now), 9 points clear, inside the 13-point floor.Standing →EnterpriseADP TotalSource67%Clear leader▲+5Since October 2026: 62% → 67%, +5 points. Inside the 13-point floor: within noise.Standing →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 rateLabelsQuadrantSince October 2026
01Justworks76%2%58endorsed leader▲+6Since October 2026: 70% → 76%, +6 points. Inside the 13-point floor: within noise.70% → 76%
Justworks76%2%58endorsed leader▲+6Since October 2026: 70% → 76%, +6 points. Inside the 13-point floor: within noise.70% → 76%02
Rippling9%2%44accepted challenger▲+3Since October 2026: 6% → 9%, +3 points. Inside the 13-point floor: within noise.6% → 9%
Rippling9%2%44accepted challenger▲+3Since October 2026: 6% → 9%, +3 points. Inside the 13-point floor: within noise.6% → 9%03
TriNet7%16%56accepted challenger▼−2Since October 2026: 9% → 7%, −2 points. Inside the 13-point floor: within noise.9% → 7%
TriNet7%16%56accepted challenger▼−2Since October 2026: 9% → 7%, −2 points. Inside the 13-point floor: within noise.9% → 7%04ADP TotalSource7%16%51accepted challenger▲+5Since October 2026: 2% → 7%, +5 points. Inside the 13-point floor: within noise.2% → 7%
ADP TotalSource7%16%51accepted challenger▲+5Since October 2026: 2% → 7%, +5 points. Inside the 13-point floor: within noise.2% → 7%05
Insperity2%22%36accepted challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 13-point floor: within noise.2% → 2%
Insperity2%22%36accepted challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 13-point floor: within noise.2% → 2%Show the two products at 0%, ordered by negative rate
06
Paychex PEO0%13%38accepted challenger▼−6Since October 2026: 6% → 0%, −6 points. Inside the 13-point floor: within noise.6% → 0%
Paychex PEO0%13%38accepted challenger▼−6Since October 2026: 6% → 0%, −6 points. Inside the 13-point floor: within noise.6% → 0%07
Deel PEO0%8%26accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 13-point floor: within noise.2% → 0%
Deel PEO0%8%26accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 13-point floor: within noise.2% → 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 can't be told apart from repeat variation, and both are shown. Each index measures its own floor from its own repeat, over its own categories, so the floor differs from one index to the next. Both editions asked the same fourteen models. How the floor is measured
Bars are the share of first choices, 0 to 100Every product with at least 10 labels here. Every product name links to its product page.
Head to headHead-to-head pages are published for mid-market buyers, so these open on mid-market figures, not small business.
All fifteen head-to-head pages: the top six products, each against each
One product takes 76% of first choices here, so the chart would put six 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. Zero products carry a negative rate above 25% in this category.
What they warned about
Seven of fourteen models held their first choice under the paraphrase. GPT-5.4 mini, Grok 4.20, Mistral Small, Llama 4 Maverick, Qwen 3.7 Flash, 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 TotalSource16%
8 of 51 labels negative · 7 of 14 models
“Another big-name PEO, ADP, was the subject of a serious data breach. While this security breach was completely preventable” Claude Haiku 4.5, negative prompt
TriNet16%
9 of 56 labels negative · 6 of 14 models · 1 hard negative
“Avoid higher-end ones like Insperity or TriNet if budget is tight” Grok 4.20, budget prompt
Insperity22%
8 of 36 labels negative · 5 of 14 models · 1 hard negative
“Avoid higher-end ones like Insperity or TriNet if budget is tight” Grok 4.20, budget prompt
Paychex PEO13%
5 of 38 labels negative · 4 of 14 models · 1 hard negative
“Some of the PEOs to avoid include: 1. Paychex - known for poor communication and high fees.” Llama 4 Maverick, negative prompt
What they cite
Fourteen of the fourteen models returned a source list in this edition: five return the pages they cited and nine the search results they consulted.
Sites the answers cite
75 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. 744 links across 165 sites, every framing counted. Ranked by the number of answers carrying the site or page. 2 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.
36 answers · 36 citations · 12 models
23 answers · 29 citations · 11 models
22 answers · 26 citations · 8 models
21 answers · 26 citations · 10 models
21 answers · 21 citations · 9 models
vendor site · G218 answers · 21 citations · 9 models
18 answers · 19 citations · 11 models
vendor site · Lead Change Group17 answers · 27 citations · 9 models
16 answers · 16 citations · 9 models
15 answers · 18 citations · 10 models
vendor site · Rework14 answers · 18 citations · 10 models
vendor site · ADP12 answers · 18 citations · 7 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.
35 answers · 11 models
22 answers · 8 models
21 answers · 9 models
17 answers · 11 models
15 answers · 8 models
15 answers · 10 models
15 answers · 9 models
15 answers · 8 models
14 answers · 11 models
12 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 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 | 76% | 279 | 60,500 | 452 | 236,868 | $2,424 | 120 | |
| Rippling rippling.com | 9% | 1438 | 301,000 | 17,886 | 712,399 | $42,013 | 115 | |
| TriNet trinet.com | 7% | 250 | 74,000 | 909 | 232,419 | $533 | 30 | |
| ADP parent site ADP TotalSource 7% | 7% | 176 | 2,740,000 | 23,897 | ||||
| Insperity insperity.com | 2% | 124 | 90,500 | 1,172 | 134,574 | $17,835 | 120 | |
| Paychex paychex.com Paychex PEO 0% | 0% | 92 | 550,000 | 4,777 | 2,394,396 company | 68 | ||
| Deel deel.com Deel PEO 0% | 0% | 49 | 40,500 | 1,210 | 307,175 company | $330,608 | 118 | 5 |
| CoAdvantage | 0% | 27,100 | 223 | |||||
| Gusto gusto.com | 0% | 742 | 673,000 | 10,560 | 1,629,483 | 118 | ||
| Remote remote.com | 0% | 249 | 110,000 | 426,655 | 766,598 | $15,858 | 88 |
Google's top ten for the three searches hold 21 sites; 1 of them are among the sites the models cited here (adp.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 choiceno first choiceHeldJustworksJustworksno first choiceagainst: ADP TotalSource
Five alternatives
CoAdvantage, Deel PEO, Insperity, Rippling, TriNetThree alternatives
Amplify PEO, Bambee PEO, OasisGPT-5.4 miniJustworksInsperity, TriNetChangedJustworksJustworksagainst: ADP TotalSource, Paychex PEO, TriNetno first choicenothing named
Five alternatives
ADP TotalSource, Deel PEO, Paychex PEO, Remote, TriNetOne alternative
PEO.comFive alternatives
ADP TotalSource, Deel PEO, Insperity, Rippling, TriNetGemini 3.5 FlashRipplingRipplingHeldJustworksJustworksno first choicenothing named
Four alternatives
ADP TotalSource, Insperity, Justworks, TriNetFour alternatives
ADP TotalSource, Insperity, Justworks, TriNetFour alternatives
ADP TotalSource, Insperity, Rippling, TriNetFour alternatives
Deel PEO, Gusto, Remote PEO, RipplingPerplexity SonarJustworksagainst: InsperityJustworksHeldJustworksJustworksagainst: Ripplingno first choicenothing named
Three alternatives
ADP TotalSource, Rippling, TriNetThree alternatives
ADP TotalSource, Insperity, TriNetSeven alternatives
ADP TotalSource, CoAdvantage, Deel PEO, Insperity, Paychex PEO, Rippling, TriNetTwo alternatives
Paychex PEO, TriNetGrok 4.20Justworks, Ripplingagainst: ADP TotalSource, Insperity, TriNetJustworksChangedJustworksagainst: InsperityJustworksagainst: Deel PEO, Insperity, TriNetno first choicenothing named
One alternative
Paychex PEOThree alternatives
ADP TotalSource, Rippling, TriNetFour alternatives
ADP TotalSource, Paychex PEO, Rippling, TriNetFour alternatives
ADP TotalSource, CoAdvantage, Paychex PEO, RipplingMistral SmallJustworksJustworks, TriNetChangedJustworksJustworksno first choicenothing named
Three alternatives
Deel PEO, Multiplier, RipplingThree alternatives
ADP TotalSource, Paychex PEO, RipplingSix alternatives
ADP TotalSource, Insperity, Papaya Global, Paychex PEO, Rippling, TriNetTwo alternatives
ADP TotalSource, TriNetDeepSeek V4 FlashJustworksJustworksHeldagainst: ADP TotalSource, TriNetJustworksagainst: InsperityJustworksagainst: ADP TotalSource, Paychex PEOno first choiceagainst: Justworks, TriNet
Four alternatives
ADP TotalSource, Paychex PEO, Rippling, TriNetOne alternative
InsperityFive alternatives
ADP TotalSource, Deel PEO, Paychex PEO, Rippling, TriNetOne alternative
GustoLlama 4 Maverickno first choiceADP TotalSourceChangedno first choiceJustworksno first choiceagainst: Paychex PEO
Three alternatives
Justworks, Paychex PEO, TriNetThree alternatives
CoAdvantage, Deel PEO, RipplingQwen 3.7 FlashJustworks, RipplingTriNetChangedJustworksJustworksno first choiceagainst: Payroll.com, TriNet
Four alternatives
Deel PEO, Insperity, Remote, TriNetFour alternatives
Caygen, Justworks, Rippling, ThripleThree alternatives
Paychex PEO, Rippling, TriNetTwo alternatives
Insperity, Paychex PEOKimi K2JustworksJustworksHeldJustworksJustworksagainst: ADP TotalSourceno first choicenothing named
Three alternatives
ADP TotalSource, Rippling, TriNetFour alternatives
ADP TotalSource, Paychex PEO, Rippling, TriNetFive alternatives
Deel PEO, Insperity, Paychex PEO, Rippling, TriNetOne alternative
BambeeGLM 4.7 FlashXJustworksJustworksHeldJustworksJustworksagainst: Deel PEOno first choiceagainst: Employee Alternatives, LLC, Oklahoma “employee-leasing” businesses, San Antonio, Texas-based PEO
Four alternatives
ADP TotalSource, Paychex PEO, Rippling, TriNetThree alternatives
ADP TotalSource, Paychex PEO, RipplingSix alternatives
ADP TotalSource, Deel PEO, Insperity, Paychex PEO, Rippling, TriNetThree alternatives
Amplify, Paychex PEO, RipplingMiniMax M2.5ADP TotalSource, JustworksJustworksChangedJustworksJustworksno first choicenothing named
Four alternatives
Gusto, Insperity, Paychex PEO, RipplingFour alternatives
ADP TotalSource, Paychex PEO, Rippling, TriNetFive alternatives
ADP TotalSource, Insperity, Paychex PEO, Rippling, TriNetFour alternatives
ADP TotalSource, Gusto, Rippling, TriNetGPT-6 LunaJustworksJustworksHeldJustworksJustworksno first choiceagainst: ADP TotalSource, Insperity, TriNet
Two alternatives
Rippling, TriNetOne alternative
RipplingFive alternatives
ADP TotalSource, Insperity, Paychex PEO, Rippling, TriNetMuse Glimmer 30BJustworksADP TotalSource, JustworksChangedJustworksJustworksagainst: ADP TotalSource, Insperity, Paychex PEO, TriNetno first choiceagainst: Deel US PEO, Insperity, Paychex PEO, Prestige PEO, TriNet
Five alternatives
ADP TotalSource, Insperity, Paychex PEO, Rippling, TriNetThree alternatives
Insperity, Rippling, TriNetThree alternatives
ADP TotalSource, Insperity, TriNetOne alternative
CoAdvantageBold is the first choiceAlternatives are counted; the count opens them.What the answer argued against
The record
One row per call: the version string exactly as returned, whether the model searched, sources cited, and latency.
Eighty-four rows: every prompt, every model, every answer.
| Prompt | Model | Version string | Time (UTC) | Searched | Sources | Latency |
|---|---|---|---|---|---|---|
| Direct recommendation | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 11:58 | no | 0 | 4 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:32 | yes | 3 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 12:08 | no | 0 | 12 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 12:38 | yes | 10 | 4 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:29 | yes | 5 | 32 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:51 | yes | 5 | 5 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 08:39 | yes | 23 | 20 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 11:03 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 09:58 | yes | 10 | 20 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 11:08 | yes | 9 | 19 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:51 | yes | 14 | 51 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 10:41 | yes | 5 | 25 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 09:02 | yes | 5 | 12 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 10:25 | yes | 12 | 18 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 12:31 | no | 0 | 5 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 11:55 | yes | 3 | 5 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 10:05 | yes | 10 | 23 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 11:22 | yes | 10 | 3 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:19 | yes | 7 | 36 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:17 | yes | 5 | 5 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 08:46 | yes | 23 | 28 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 10:01 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:01 | no | 0 | 25 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:44 | yes | 19 | 50 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 11:25 | yes | 17 | 69 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 11:05 | yes | 11 | 61 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 08:38 | yes | 2 | 13 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 10:38 | yes | 15 | 22 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 12:52 | yes | 9 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:25 | yes | 10 | 12 s |
| Comparative | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 08:40 | yes | 10 | 24 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 12:17 | yes | 10 | 6 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:04 | yes | 5 | 42 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 08:48 | yes | 5 | 6 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:19 | yes | 21 | 25 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 12:24 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:04 | yes | 5 | 27 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 11:23 | yes | 9 | 22 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:20 | yes | 8 | 64 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 11:30 | yes | 10 | 36 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 12:53 | yes | 7 | 22 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:53 | yes | 22 | 36 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 08:52 | yes | 15 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:50 | yes | 2 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 11:09 | yes | 6 | 17 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 08:39 | yes | 10 | 4 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:05 | yes | 10 | 33 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:34 | yes | 5 | 6 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 11:13 | yes | 22 | 26 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 11:33 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 10:25 | yes | 5 | 29 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:18 | yes | 15 | 56 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:36 | yes | 11 | 95 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 09:32 | yes | 5 | 74 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 10:23 | yes | 2 | 13 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 11:10 | yes | 23 | 21 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 11:25 | no | 0 | 9 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:07 | no | 0 | 7 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 11:46 | no | 0 | 19 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 12:30 | yes | 10 | 7 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:28 | yes | 5 | 65 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:38 | no | 0 | 7 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:05 | yes | 19 | 30 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 11:16 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 10:57 | yes | 5 | 27 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:03 | yes | 9 | 43 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 11:44 | yes | 15 | 129 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 08:53 | yes | 10 | 47 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 09:41 | yes | 4 | 19 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:38 | yes | 14 | 27 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 08:51 | yes | 18 | 8 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 11:13 | yes | 4 | 5 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:23 | yes | 6 | 15 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 08:52 | yes | 10 | 4 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:23 | yes | 5 | 30 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 09:42 | yes | 5 | 6 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 08:50 | yes | 23 | 41 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 12:58 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 09:42 | no | 0 | 32 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 08:42 | yes | 15 | 44 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 12:21 | yes | 22 | 32 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 12:29 | yes | 5 | 52 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:36 | yes | 3 | 19 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:15 | yes | 22 | 27 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
Deel read as Deel PEO
Paychex read as Paychex PEO
Unresolved, counted raw
Bambee PEO
Caygen
Deel US PEO
Employee Alternatives, LLC (North Carolina)
Insperity PEO Services
NetPEO
Oklahoma “employee-leasing” businesses
Optic
PEO.com
Papaya Global PEO
Payroll.com
Prestige PEO
Rippling PEO Services
San Antonio, Texas-based PEO (multiple entities)
Thriple
TriNet PEO Services
Discontinued, still offered
No shut-down product was recommended here.