Performance management
Asked as “performance management software”, and as “performance review tool”, on behalf of a mid-market B2B company. 46 first choices recorded across the direct, paraphrase, budget and scale prompts, twelve models each.
Standing · first-choice share
41%
Clear leader
41Lattice11Effy AI09PerformYard39others
41% 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 twelve models, for a mid-market B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrant
Show the five products 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.
All twenty-eight head-to-head pages: the top eight products, each against each
Lattice vs Small ImprovementsLattice vs BetterworksLattice vs LeapsomeLattice vs Culture AmpPerformYard vs 15FivePerformYard vs HiBobPerformYard vs Small ImprovementsPerformYard vs BetterworksPerformYard vs LeapsomePerformYard vs Culture Amp15Five vs HiBob15Five vs Small Improvements15Five vs Betterworks15Five vs Leapsome15Five vs Culture AmpHiBob vs Small ImprovementsHiBob vs BetterworksHiBob vs LeapsomeHiBob vs Culture AmpSmall Improvements vs BetterworksSmall Improvements vs LeapsomeSmall Improvements vs Culture AmpBetterworks vs LeapsomeBetterworks vs Culture AmpLeapsome vs Culture Amp
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
07
08
09
10
11
12
13
14Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative60%
Key
01Lattice41%
Lattice41%02PerformYard9%
PerformYard9%0315Five7%
15Five7%04HiBob7%
HiBob7%05Small Improvements7%
Small Improvements7%06Betterworks4%
Betterworks4%07Leapsome2%
Leapsome2%08Culture Amp2%
Culture Amp2%09Teamflect2%
Teamflect2%10Profit.co0%
Profit.co0%11Rippling0%
Rippling0%12BambooHR0%
BambooHR0%13Workday HCM Performance Management0%
Workday HCM Performance Management0%14SAP SuccessFactors0%
SAP SuccessFactors0%What they warned about
Four of twelve models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Grok 4.20, Mistral Small, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2 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.
BambooHR30%
10 of 33 labels negative · 7 of 12 models · 2 hard negative
“Reviews frequently cite "limited features"... Verdict: Avoid if you need actionable data, detailed analytics, or a flexible review process.” Qwen 3.7 Flash, negative prompt
Workday HCM Performance Management48%
11 of 23 labels negative · 6 of 12 models · 2 hard negative
“(Avoid enterprise monsters like Workday Performance unless you are already fully committed to the broader Workday ecosystem, as they are often too rigid and expensive” Gemini 3.5 Flash, scale prompt
Lattice12%
6 of 51 labels negative · 5 of 12 models · 1 hard negative
“Watch Out For: Minimum seat requirements (e.g., Lattice requires $4,000/year minimum)” Kimi K2, budget prompt
SAP SuccessFactors67%
8 of 12 labels negative · 5 of 12 models · 1 hard negative
“Steep learning curve, poor UI, rigid customization | Non-technical HR teams. Avoid unless you have consultants on retainer.” DeepSeek V4 Flash, negative prompt
What they cite
Twelve of the twelve models returned a source list in this edition: four return the pages they cited and eight the search results they consulted.
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. 895 links across 200 sites, every framing counted. Ranked by the number of answers carrying the site or page.
42 answers · 45 citations · 11 models
vendor site · Betterworks34 answers · 48 citations · 12 models
vendor site · OKRs Tool29 answers · 30 citations · 11 models
vendor site · G226 answers · 28 citations · 11 models
25 answers · 25 citations · 11 models
vendor site · G220 answers · 48 citations · 11 models
vendor site · Teamflect20 answers · 24 citations · 10 models
vendor site · Workhuman19 answers · 19 citations · 9 models
18 answers · 23 citations · 8 models
vendor site · Effy15 answers · 18 citations · 11 models
15 answers · 16 citations · 10 models
vendor site · Gartner13 answers · 20 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.
38 answers · 10 models
29 answers · 11 models
25 answers · 10 models
24 answers · 11 models
20 answers · 10 models
18 answers · 9 models
17 answers · 9 models
14 answers · 10 models
14 answers · 9 models
13 answers · 6 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 performance management software”, “performance management platforms”, “performance management software”. 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 |
|---|---|---|---|---|---|---|---|
| Lattice lattice.com | 41% | 625 | 90,500 | 13,900 | 122,123 | $1,328 | 120 |
| Effy effy.ai Effy AI 11% | 11% | 77 | 140 | 3 | 40,950 company | ||
| PerformYard performyard.com | 9% | 217 | 9,900 | 34 | 58,643 | $25 | 47 |
| 15Five 15five.com | 7% | 352 | 6,600 | 32 | 32,362 | 22 | |
| HiBob hibob.com | 7% | 354 | 14,800 | 154 | 266,143 | $54 | 120 |
| Small Improvements small-improvements.com | 7% | 92 | 1,000 | 137 | 43,657 | 1 | |
| Betterworks betterworks.com | 4% | 220 | 3,600 | 21 | 12,379 | 0 | |
| Leapsome leapsome.com | 2% | 378 | 2,900 | 32 | 51,450 | $18,531 | 60 |
| Culture Amp cultureamp.com | 2% | 354 | 14,800 | 121 | 174,918 | 35 | |
| Teamflect teamflect.com | 2% | 136 | 880 | 12 | 12,592 | 30 |
Google's top ten for the three searches hold 18 sites; 4 of them are among the sites the models cited here (forbes.com, gartner.com, learn.g2.com, selectsoftwarereviews.com). The first result for “best performance management software” is learn.g2.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 performance management software for a mid-market B2B company?”Paraphrase“Which performance review tool would you recommend to a mid-sized B2B company?”Comparative“What are the top performance management platforms and how do they differ?”Budget-constrained“What is the best performance management software for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a performance management software. What should we look at?”Negative“Which performance management platforms should I avoid or be cautious about?”
Claude Haiku 4.5LatticeHiBobChangedno first choiceZoho Peopleno first choiceagainst: BambooHR, ThriveSparrow
Six alternatives
15Five, Betterworks, Culture Amp, HiBob, Leapsome, PerformYardThree alternatives
BambooHR, Namely, ThriveSparrowEight alternatives
15Five, Betterworks, Lattice, Leapsome, Oracle Fusion Cloud HCM, PerformYard, SAP SuccessFactors, Workday HCM Performance ManagementThree alternatives
Effy AI, Small Improvements, TeamflectGPT-5.4 miniLattice15FiveChangedno first choicePerformno first choicenothing named
One alternative
Mitratech PerformTwo alternatives
Culture Amp, PerformYardOne alternative
PerformYardGemini 3.5 FlashLatticeagainst: SAP SuccessFactors, Workday HCM Performance ManagementLatticeHeldLatticeTeamflectagainst: Culture Amp, Lattice15Five, Culture Amp, Lattice, Leapsome, PerformYardagainst: Workday HCM Performance Managementagainst: Oracle Fusion Cloud HCM, SAP SuccessFactors, Workday HCM Performance Management
Four alternatives
15Five, Betterworks, HiBob, LeapsomeFive alternatives
15Five, HiBob, Leapsome, Rippling, TeamflectSix alternatives
15Five, Betterworks, Culture Amp, Leapsome, PerformYard, TeamflectFive alternatives
15Five, EvalFlow, Odoo, PerformYard, SentrifugoPerplexity SonarLatticeLatticeHeldLatticeEffy AIno first choiceagainst: 15Five, BambooHR, Lattice, Rippling, SAP SuccessFactors, Workday HCM Performance Management
Four alternatives
15Five, Betterworks, HiBob, LeapsomeFour alternatives
15Five, BambooHR, Betterworks, PerformYardSix alternatives
15Five, BambooHR, Betterworks, Leapsome, PerformYard, Workday HCM Performance ManagementThree alternatives
Profit.co, Small Improvements, Zoho PeopleGrok 4.20Latticeagainst: Workday HCM Performance Management15FiveChangedno first choiceAssessTEAM, Performance Prono first choiceagainst: ADP Workforce Now, BambooHR, Gusto, Rippling, UKG Pro, Workday HCM Performance Management
Four alternatives
15Five, HiBob, Leapsome, PaylocityFour alternatives
Lattice, Leapsome, PerformYard, ThriveSparrowThree alternatives
Small Improvements, WebHR, Zoho PeopleMistral SmallLatticePerformYardChangedno first choiceSmall Improvementsno first choiceagainst: Culture Amp, HelloTeam, Namely, Reflektive
Two alternatives
15Five, Culture AmpTwo alternatives
Betterworks, TrakstarThree alternatives
15Five, Effy AI, TrakstarDeepSeek V4 FlashLatticeLatticeHeldLatticeEffy AIagainst: BambooHRLatticeagainst: SAP, Workday HCM Performance Managementagainst: AssessTEAM, BambooHR, Cornerstone OnDemand, Gusto, Keka, Lattice, Leapsome, Mitratech Perform, PerformYard, SAP SuccessFactors, Workday HCM Performance Management
Five alternatives
15Five, Betterworks, Culture Amp, Leapsome, PerformYardFive alternatives
15Five, BambooHR, Culture Amp, HiBob, LeapsomeSeven alternatives
15Five, BambooHR, Betterworks, Culture Amp, HiBob, Leapsome, RipplingThree alternatives
PerformYard, Small Improvements, WebHRTwo alternatives
15Five, BetterworksLlama 4 MaverickBetterworks, HiBob, LatticeHiBobChangedno first choiceSmall Improvementsno first choiceagainst: 15Five, Lattice, Leapsome, PerformYard
Three alternatives
Betterworks, Engagedly, TrakstarTwo alternatives
Trakstar, Zoho PeopleQwen 3.7 FlashLatticeBetterworksChangedLatticeagainst: BambooHRSmall Improvementsno first choiceagainst: SAP SuccessFactors, Workday HCM Performance Managementagainst: BambooHR, Betterworks, Gusto, Oracle Fusion Cloud HCM, SAP SuccessFactors
Three alternatives
15Five, Betterworks, HiBobThree alternatives
HiBob, Lattice, TrakstarFour alternatives
15Five, Betterworks, SAP SuccessFactors, Workday HCM Performance ManagementFour alternatives
AssessTEAM, Effy AI, Profit.co, Zoho PeopleFour alternatives
15Five, Culture Amp, Divalent, LatticeKimi K2LatticePerformYardChangedLatticeEffy AIagainst: Lattice, Small Improvementsno first choiceagainst: 15Five, BambooHR, Betterworks, Lattice
Four alternatives
15Five, Culture Amp, Leapsome, PerformYardTwo alternatives
15Five, LatticeSix alternatives
15Five, BambooHR, Culture Amp, Leapsome, Rippling, Workday HCM Performance ManagementFive alternatives
EvalFlow, OrangeHRM, Profit.co, Synergita PMS, Zoho PeopleThree alternatives
Betterworks, Lattice, PerformYardGLM 4.7 FlashXLatticeagainst: SAP SuccessFactors, Workday HCM Performance ManagementLatticeHeldno first choiceEffy AILatticeagainst: BambooHR, SAP SuccessFactors, Workday HCM Performance Managementagainst: BambooHR, Betterworks, Deel, Mitratech Perform
Five alternatives
15Five, Culture Amp, HiBob, Leapsome, RipplingFive alternatives
15Five, BambooHR, Leapsome, Rippling, TeamflectThree alternatives
PerformYard, Profit.co, Small ImprovementsFour alternatives
15Five, Betterworks, ClearCompany, LeapsomeMiniMax M2.5LatticePerformYardChangedLattice, ThriveSparrowEffy AIno first choicenothing named
Two alternatives
Engagedly, PaylocityOne alternative
LatticeTwo alternatives
Betterworks, RipplingThree alternatives
BambooHR, Profit.co, Small ImprovementsBold 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.
Seventy-two 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 | 2026-09-17 18:50 | yes | 9 | 7 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 19:10 | yes | 3 | 4 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 22:06 | yes | 19 | 56 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-09-17 21:08 | yes | 20 | 5 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 18:18 | yes | 40 | 18 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 21:13 | yes | 15 | 11 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 21:37 | yes | 9 | 11 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:12 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 19:09 | yes | 14 | 40 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 20:28 | yes | 13 | 38 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 21:39 | yes | 12 | 80 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 21:04 | yes | 5 | 17 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:55 | yes | 9 | 8 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 18:15 | yes | 2 | 7 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 22:03 | yes | 8 | 50 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-09-17 19:35 | yes | 20 | 7 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 21:16 | yes | 32 | 15 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 20:27 | yes | 5 | 3 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 21:23 | yes | 8 | 11 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:54 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 21:13 | yes | 5 | 24 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 21:34 | yes | 10 | 18 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 21:10 | yes | 13 | 354 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:30 | yes | 15 | 30 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 20:01 | yes | 16 | 11 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 18:20 | yes | 9 | 12 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 21:53 | yes | 17 | 47 s |
| Comparative | Perplexity Sonar | sonar | 2026-09-17 18:35 | yes | 20 | 14 s |
| Comparative | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 20:50 | yes | 32 | 16 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 19:46 | yes | 9 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 21:03 | yes | 16 | 21 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:13 | yes | 5 | 3 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 20:59 | yes | 10 | 40 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 20:45 | yes | 15 | 40 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 18:23 | yes | 9 | 59 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 20:39 | yes | 5 | 16 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 20:14 | yes | 9 | 8 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 20:54 | yes | 2 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 18:36 | yes | 23 | 22 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-09-17 19:11 | yes | 20 | 7 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 19:54 | yes | 41 | 17 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 17:56 | yes | 5 | 5 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 20:42 | yes | 8 | 11 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:12 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 21:28 | yes | 5 | 27 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:36 | yes | 10 | 21 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 21:11 | yes | 16 | 46 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 20:57 | yes | 9 | 23 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:55 | no | 0 | 6 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 20:44 | no | 0 | 6 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 20:00 | no | 0 | 14 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-09-17 19:18 | yes | 20 | 11 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 19:05 | yes | 12 | 10 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 19:10 | no | 0 | 7 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 18:50 | yes | 10 | 17 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 21:25 | yes | 5 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 20:32 | no | 0 | 28 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 21:38 | yes | 25 | 37 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 21:11 | yes | 14 | 55 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 21:04 | no | 0 | 8 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 20:47 | yes | 18 | 8 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 21:27 | no | 0 | 3 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 18:46 | yes | 18 | 21 s |
| Negative framing | Perplexity Sonar | sonar | 2026-09-17 20:26 | yes | 20 | 9 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 20:14 | yes | 36 | 20 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 21:07 | yes | 5 | 5 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-17 19:00 | yes | 25 | 71 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:35 | yes | 8 | 4 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 18:14 | yes | 9 | 44 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 17:53 | yes | 23 | 29 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 19:01 | yes | 18 | 32 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:42 | yes | 17 | 35 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
1 of 3 flipped
GPT-5.4 mini
4 of 4 flipped
Gemini 3.5 Flash
3 of 5 flipped
Perplexity Sonar
1 of 4 flipped
Grok 4.20
4 of 4 flipped
Mistral Small
1 of 3 flipped
DeepSeek V4 Flash
2 of 5 flipped
Llama 4 Maverick
2 of 4 flipped
Qwen 3.7 Flash
4 of 5 flipped
Kimi K2
2 of 4 flipped
GLM 4.7 FlashX
4 of 5 flipped
MiniMax M2.5
2 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
Bob (HiBob) read as HiBob
Deel HR read as Deel
HiBob / Bob read as HiBob
HiBob HRIS read as HiBob
Odoo Appraisal read as Odoo
Oracle HCM read as Oracle Fusion Cloud HCM
Workday read as Workday HCM Performance Management
Workday HCM read as Workday HCM Performance Management
Workday Performance read as Workday HCM Performance Management
Workday Performance & Talent Management read as Workday HCM Performance Management
Workday Performance Layer read as Workday HCM Performance Management
Workday Talent Management read as Workday HCM Performance Management
Unresolved, counted raw
HelloTeam
Perform
Synergita PMS
Discontinued, still offered
No shut-down product was recommended here.