Knowledge base and self-service for small business buyers
Asked as “knowledge base software”, and as “customer self-service help center tool”, on behalf of a small B2B company. 49 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
41%
Clear leader
41Notion14Help Scout Docs10Zoho Desk35others
41% of first choices, clear leader.
Since September 2026▲+4Since September 2026: 38% → 42%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Notion held the lead, +4 points on 38%, inside the 11-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
Notion41%Clear leader▲+4Since September 2026: 38% → 42%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.This pageMid-marketNotion21%Contested▲+4Since September 2026: 18% → 22%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Standing →Enterprise
Zendesk Guide28%Contested↗new leaderNew leader since September 2026: Confluence (28%) replaces Zendesk Guide (30% then, 26% now), 2 points clear, inside the 11-point floor.Standing →
Notion41%Clear leader▲+4Since September 2026: 38% → 42%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.This pageMid-marketNotion21%Contested▲+4Since September 2026: 18% → 22%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Standing →EnterpriseZendesk Guide28%Contested↗new leaderNew leader since September 2026: Confluence (28%) replaces Zendesk Guide (30% then, 26% now), 2 points clear, inside the 11-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 small B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrantSince September 2026
01Notion41%12%56endorsed leader▲+4Since September 2026: 38% → 42%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.38% → 42%
Notion41%12%56endorsed leader▲+4Since September 2026: 38% → 42%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.38% → 42%02
Help Scout Docs14%0%33accepted challenger▲+4Since September 2026: 10% → 14%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.10% → 14%
Help Scout Docs14%0%33accepted challenger▲+4Since September 2026: 10% → 14%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.10% → 14%03
Zoho Desk10%0%12accepted challenger▲+4Since September 2026: 7% → 12%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.7% → 12%
Zoho Desk10%0%12accepted challenger▲+4Since September 2026: 7% → 12%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.7% → 12%04
Freshdesk6%0%16accepted challenger▼−7Since September 2026: 12% → 5%, −7 points. Inside the 11-point floor: within noise. Read over the models both editions asked.12% → 5%
Freshdesk6%0%16accepted challenger▼−7Since September 2026: 12% → 5%, −7 points. Inside the 11-point floor: within noise. Read over the models both editions asked.12% → 5%05
Document3604%24%34accepted challenger▲+2Since September 2026: 2% → 5%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 5%
Document3604%24%34accepted challenger▲+2Since September 2026: 2% → 5%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 5%06
Slab2%0%22accepted challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%
Slab2%0%22accepted challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%07
Nuclino2%0%16accepted challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%
Nuclino2%0%16accepted challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%08
BookStack2%8%12accepted challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%
BookStack2%8%12accepted challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%09Zendesk Guide2%56%27criticized challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%
Zendesk Guide2%56%27criticized challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%Show the eight products at 0%, ordered by negative rate
17
Intercom Articles0%38%13criticized challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%
Intercom Articles0%38%13criticized challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%15
Confluence0%37%41criticized challenger▼−5Since September 2026: 5% → 0%, −5 points. Inside the 11-point floor: within noise. Read over the models both editions asked.5% → 0%
Confluence0%37%41criticized challenger▼−5Since September 2026: 5% → 0%, −5 points. Inside the 11-point floor: within noise. Read over the models both editions asked.5% → 0%12
Guru0%24%25accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
Guru0%24%25accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%16
Helpjuice0%23%13accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
Helpjuice0%23%13accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%14
ClickUp0%10%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
ClickUp0%10%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%13
HelpDocs0%10%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
HelpDocs0%10%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%11
Tettra0%5%21accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
Tettra0%5%21accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%10
Slite0%0%27accepted challenger▼−10Since September 2026: 10% → 0%, −10 points. Inside the 11-point floor: within noise. Read over the models both editions asked.10% → 0%
Slite0%0%27accepted challenger▼−10Since September 2026: 10% → 0%, −10 points. Inside the 11-point floor: within noise. Read over the models both editions asked.10% → 0%The floor is 11 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-eight head-to-head pages: the top eight products, each against each
Notion vs ConfluenceNotion vs SliteNotion vs HelpjuiceNotion vs HubSpot Service HubDocument360 vs FreshdeskDocument360 vs Zendesk GuideDocument360 vs ConfluenceDocument360 vs SliteDocument360 vs HelpjuiceDocument360 vs HubSpot Service HubFreshdesk vs Zendesk GuideFreshdesk vs ConfluenceFreshdesk vs SliteFreshdesk vs HelpjuiceFreshdesk vs HubSpot Service HubZendesk Guide vs ConfluenceZendesk Guide vs SliteZendesk Guide vs HelpjuiceZendesk Guide vs HubSpot Service HubConfluence vs SliteConfluence vs HelpjuiceConfluence vs HubSpot Service HubSlite vs HelpjuiceSlite vs HubSpot Service HubHelpjuice vs HubSpot Service Hub
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 →
0102030405060708091011121314151617Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative60%
Key
01Notion41%
Notion41%02Help Scout Docs14%
Help Scout Docs14%03Zoho Desk10%
Zoho Desk10%04Freshdesk6%
Freshdesk6%05Document3604%
Document3604%06Slab2%
Slab2%07Nuclino2%
Nuclino2%08BookStack2%
BookStack2%09Zendesk Guide2%
Zendesk Guide2%10Slite0%
Slite0%11Tettra0%
Tettra0%12Guru0%
Guru0%13HelpDocs0%
HelpDocs0%14ClickUp0%
ClickUp0%15Confluence0%
Confluence0%16Helpjuice0%
Helpjuice0%17Intercom Articles0%
Intercom Articles0%What they warned about
Two of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Gemini 3.5 Flash, Grok 4.1 Fast, Mistral Small, DeepSeek V4 Flash, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, GLM 4.7 FlashX, GPT-6 Luna 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.
Confluence37%
15 of 41 labels negative · 10 of 14 models · 5 hard negative
“Tools to **Avoid or Be Cautious About**: 1. **Atlassian Confluence**... "too expensive for small businesses or startups."” Grok 4.1 Fast, negative prompt
Zendesk Guide56%
15 of 27 labels negative · 9 of 14 models · 4 hard negative
“Why to Avoid: Zendesk is the gold standard for large-scale support, but its pricing model is aggressive.” Qwen 3.7 Flash, negative prompt
Document36024%
8 of 34 labels negative · 7 of 14 models · 2 hard negative
“Customer-facing emphasis with custom quotes, advanced AI/analytics that small teams rarely need. High setup time and costs” Grok 4.1 Fast, negative prompt
Notion12%
7 of 56 labels negative · 6 of 14 models
“Notion, for example, supports HTML, Markdown, and CSV exports, but says an export can’t instantly recreate the workspace, and some inaccessible pages may be left out.” GPT-6 Luna, 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
73 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. 900 links across 187 sites, every framing counted. Ranked by the number of answers carrying the site or page. 4 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.
43 answers · 48 citations · 12 models
27 answers · 35 citations · 9 models
vendor site · Slite25 answers · 32 citations · 10 models
vendor site · KnowledgeOwl22 answers · 24 citations · 12 models
vendor site · MangoApps22 answers · 22 citations · 10 models
vendor site · Document36020 answers · 24 citations · 9 models
vendor site · Helply19 answers · 21 citations · 11 models
17 answers · 19 citations · 10 models
vendor site · Zendesk17 answers · 19 citations · 10 models
vendor site · HelpDocs16 answers · 21 citations · 6 models
vendor site · Plain16 answers · 21 citations · 10 models
vendor site · Ferndesk16 answers · 17 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.
31 answers · 11 models
24 answers · 9 models
22 answers · 10 models
22 answers · 9 models
17 answers · 8 models
17 answers · 10 models
15 answers · 8 models
15 answers · 9 models
14 answers · 5 models
13 answers · 7 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 knowledge base software”, “knowledge base 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 |
|---|---|---|---|---|---|---|---|
| Notion notion.com | 41% | 209 | 673,000 | 15,608 | 1,061,466 | 52 | |
| Help Scout Docs helpscout.com | 14% | 55 | 70 | 0 | 37,899 | 14 | |
| Zoho parent site Zoho Desk 10% | 10% | 130 | 8,100 | 105 | |||
| ProProfs Knowledge Base proprofs.com | 8% | 9 | |||||
| Helply helply.com | 8% | 25 | 210 | 7 | 9,626 | 0 | |
| Freshworks freshworks.com Freshdesk 6% | 6% | 283 | 12,100 | 391 | 111,586 company | $14,486 | 113 |
| Document360 document360.com | 4% | 105 | 1,300 | 20 | 15,294 | $648 | 92 |
| Slab slab.com | 2% | 32 | 27,100 | 55,130 | 17,637 | ||
| Nuclino nuclino.com | 2% | 28 | 1,600 | 21 | 10,489 | 0 | |
| BookStack bookstackapp.com | 2% | 23 | 12,100 | 98 | 9,396 |
Google's top ten for the two searches hold 16 sites; 3 of them are among the sites the models cited here (ferndesk.com, helpdocs.io, slite.com). The first result for “best knowledge base software” is ferndesk.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 knowledge base software for a small B2B company?”Paraphrase“Which customer self-service help center tool would you recommend to a small business that sells to other businesses?”Comparative“What are the top knowledge base tools for a small team and how do they differ?”Budget-constrained“What is the best knowledge base software for a small company with a tight budget?”Scale-constrained“We are a 30 person company evaluating a knowledge base software. What should we look at?”Negative“Which knowledge base tools should a small business avoid or be cautious about?”
Claude Haiku 4.5Notionno first choiceChangedHelp Scout Docs, NotionNotionagainst: MediaWikino first choiceagainst: Confluence, Document360, Guru, Notion, Obsidian, ServiceNow Knowledge Management, Stonly, Zendesk Guide
Two alternatives
Document360, Zendesk GuideThree alternatives
Nuclino, Slite, TettraSix alternatives
Confluence, Document360, GitHub Wiki, Helpjuice, Slite, Zendesk GuideGPT-5.4 miniNotionZendesk GuideChangedNotion, SlabNotionagainst: Document360, KnowledgeOwlno first choicenothing named
Three alternatives
Confluence, GitBook, GuruOne alternative
Intercom ArticlesThree alternatives
Confluence, GitBook, Jira Service Management KB + ConfluenceOne alternative
HelpCenter.ioGemini 3.5 FlashHelp Scout Docs, NotionDocument360Changedagainst: Intercom ArticlesNotionagainst: Document360Notion, Zoho Deskno first choiceagainst: Confluence, Zendesk Guideagainst: Airtable, Coda, Confluence, Dropbox, Google Drive, Intercom Articles, MS Teams Files, Notion, Salesforce Knowledge, SharePoint, Zendesk Guide
Four alternatives
Document360, Guru, Helpjuice, SliteThree alternatives
Help Scout Docs, HubSpot Service Hub, StonlyFour alternatives
Confluence, Guru, Help Scout Docs, SlabSeven alternatives
BookStack, Confluence, Echo Knowledge Base, Enjo, GitBook, Slab, WeDocsFive alternatives
Document360, Guru, Help Scout Docs, Notion, Slab or SlitePerplexity SonarHelp Scout DocsHelp Scout DocsHeldNotionNuclino, ProProfs Knowledge Baseno first choiceagainst: Confluence, Helply, ServiceNow Knowledge Management, Zendesk Guide, eXo Platform
Five alternatives
BookStack, Helply, Notion, Nuclino, PylonThree alternatives
Intercom Articles, Zendesk Guide, Zoho DeskFour alternatives
BookStack, Document360, Nuclino, SliteOne alternative
Help Scout DocsGrok 4.1 FastNotionagainst: Confluence, Document360, GitBook, Guru, HelpjuiceHelp Scout DocsChangedagainst: Intercom Articles, Zendesk GuideNotionagainst: Confluence, GuruBookStack, Notionagainst: Helpjuice, Outlineno first choiceagainst: Confluence, Document360, Guru, Notion, Stonly, Zendesk Guide
Three alternatives
BoldDesk, Nuclino, TettraOne alternative
Zoho DeskFour alternatives
Nuclino, Slab, Slite, TettraThree alternatives
ClickUp, Confluence, ProProfs Knowledge BaseMistral SmallHelplyno first choiceChangedNotionagainst: BloomfireNotion, ProProfs Knowledge Baseno first choiceagainst: Confluence, Zendesk Guideagainst: Document360, Guru, Stonly
Two alternatives
Freshdesk, Help Scout DocsTwo alternatives
Help Scout Docs, TettraTwo alternatives
Guru, SliteDeepSeek V4 FlashDocument360, NotionFreshdeskChangedagainst: Zendesk GuideNotionNotionNotionagainst: Confluenceagainst: Bloomfire, BookStack, ClickUp, Confluence, Freshdesk AI, Glean, MediaWiki, Microsooft SharePoint, Notion, ServiceNow Knowledge Management, Zendesk Guide
Three alternatives
Guru, Help Scout Docs, SliteThree alternatives
Document360, Help Scout Docs, Zoho DeskFive alternatives
Confluence, Guru, Help Scout Docs, Slab, SliteThree alternatives
ClickUp, ProProfs Knowledge Base, TettraThree alternatives
Document360, Slite, TettraLlama 4 MaverickHelplyZoho DeskChangedno first choiceProProfs Knowledge Baseno first choicenothing named
Three alternatives
Document360, Freshdesk, Zoho DeskFive alternatives
Freshdesk, HubSpot Service Hub, Intercom Articles, Plain, Zendesk for Customer ServiceFour alternatives
ClickUp, Confluence, Notion, NuclinoQwen 3.7 FlashHelp Scout Docsagainst: Zendesk GuideFreshdeskChangedagainst: HubSpot Service HubNotionagainst: ConfluenceNotionagainst: Intercom Articles, Zendesk Guideno first choiceagainst: Confluence, Discord, Docebo, Google Drive, Microsoft Teams, Moodle, Notion, OneDrive, Salesforce Knowledge, ServiceNow Knowledge Management, SharePoint, Slack, Zendesk Guide, Zendesk Sunshine
Two alternatives
Freshdesk, PylonTwo alternatives
Help Scout Docs, Zoho DeskThree alternatives
GitBook, Help Scout Docs, SliteTwo alternatives
BookStack, SlabSix alternatives
Document360, Freshdesk, Intercom Articles, Knowledgetree, Notion, Zendesk GuideKimi K2Notionagainst: Zendesk GuideHelp Scout DocsChangedHelp Scout Docs, NotionNotionagainst: Document360, TettraNotionagainst: Confluence, Helpjuice, Intercom Articles, Zendesk Guide
Four alternatives
Confluence, Document360, Guru, Help Scout DocsTwo alternatives
Notion, Zendesk GuideFive alternatives
Confluence, Document360, HelpDocs, Slab, TettraThree alternatives
ClickUp, Confluence, NuclinoFour alternatives
ClickUp, Document360, Guru, Help Scout DocsGLM 4.7 FlashXHelplyagainst: PlainZoho DeskChangedNotion, Slab, Sliteagainst: Confluence, GuruNotion, ProProfs Knowledge Baseagainst: HelpDocsno first choicenothing named
Five alternatives
Assembly, Help Scout Docs, HelpDocs, Notion, Zoho DeskFour alternatives
Freshdesk, Helply, HubSpot Service Hub, TeamSupportOne alternative
TettraThree alternatives
BookStack, ClickUp, DokuWikiMiniMax M2.5Zoho DeskZoho DeskHeldno first choiceNotionno first choicenothing named
Four alternatives
Confluence, Knowmax, Notion, SlabTwo alternatives
Freshdesk, Zendesk GuideThree alternatives
BookStack, Confluence, Wiki.jsGPT-6 LunaNotionagainst: Document360Help Scout DocsChangedNotionSlabagainst: Notionno first choiceagainst: Notion
One alternative
Help Scout DocsOne alternative
FreshdeskFive alternatives
Confluence, Document360, Guru, Slab, Zendesk GuideTwo alternatives
BookStack, ConfluenceMuse Glimmer 30BHelplyFreshdeskChangedNotion, SlabNotionno first choiceagainst: Confluence, Zendesk Guide
Two alternatives
Help Scout Docs, NotionThree alternatives
Document360, Help Scout Docs, Zoho DeskFour alternatives
Confluence, Guru, Help Scout Docs, TettraFour alternatives
HelpDocs, ProProfs Knowledge Base, ProductLift, SlabBold 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 13:26 | no | 0 | 5 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:29 | yes | 3 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:35 | yes | 12 | 16 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-01 07:41 | yes | 22 | 2 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 12:13 | yes | 23 | 9 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 09:31 | yes | 5 | 2 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:12 | yes | 13 | 21 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 07:26 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 11:18 | yes | 10 | 36 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 13:53 | yes | 14 | 31 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 12:00 | yes | 16 | 84 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:37 | yes | 9 | 11 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:36 | yes | 3 | 11 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 13:17 | yes | 12 | 15 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 08:11 | no | 0 | 4 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:37 | yes | 5 | 5 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:14 | yes | 11 | 20 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-01 12:43 | yes | 17 | 3 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 08:01 | yes | 24 | 5 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 07:36 | no | 0 | 2 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 12:25 | yes | 25 | 30 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 10:04 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:40 | yes | 10 | 37 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 12:56 | yes | 14 | 21 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 12:35 | yes | 24 | 148 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 10:39 | yes | 6 | 19 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:14 | yes | 2 | 17 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 14:08 | yes | 15 | 19 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 08:37 | yes | 9 | 9 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 12:14 | yes | 3 | 7 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:17 | yes | 11 | 20 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-01 08:25 | yes | 19 | 4 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 07:47 | yes | 18 | 7 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 08:36 | yes | 10 | 6 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 12:18 | yes | 19 | 20 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:15 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 10:08 | yes | 10 | 17 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 08:08 | yes | 15 | 26 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 11:50 | yes | 16 | 58 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:18 | yes | 13 | 27 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:01 | yes | 5 | 14 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:34 | yes | 13 | 21 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 12:58 | no | 0 | 5 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 09:14 | yes | 3 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:09 | yes | 14 | 24 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-01 11:05 | yes | 17 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 08:31 | yes | 18 | 8 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 07:57 | yes | 5 | 4 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 07:47 | yes | 17 | 10 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:21 | yes | 5 | 1 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:07 | yes | 5 | 35 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 09:12 | yes | 11 | 26 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 09:15 | yes | 15 | 47 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 07:45 | yes | 5 | 11 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 13:29 | yes | 4 | 13 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 10:47 | yes | 13 | 28 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 10:08 | no | 0 | 5 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:36 | no | 0 | 5 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 12:41 | no | 0 | 14 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-01 12:51 | yes | 18 | 4 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 08:09 | yes | 12 | 7 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:56 | no | 0 | 7 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 12:56 | yes | 18 | 39 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 07:28 | yes | 5 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 14:14 | no | 0 | 27 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 10:42 | yes | 15 | 56 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:15 | yes | 13 | 105 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:01 | no | 0 | 8 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 08:19 | yes | 3 | 15 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 07:52 | yes | 13 | 25 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 11:16 | yes | 15 | 9 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 10:41 | no | 0 | 3 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 10:35 | yes | 9 | 20 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-01 09:50 | yes | 21 | 4 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 11:03 | yes | 20 | 8 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:34 | yes | 5 | 6 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 13:41 | yes | 23 | 43 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 12:58 | yes | 5 | 1 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 12:06 | yes | 23 | 55 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 11:54 | yes | 21 | 24 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 14:02 | yes | 19 | 86 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 12:08 | yes | 16 | 41 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:01 | yes | 2 | 14 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 08:04 | yes | 21 | 39 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
Help Scout read as Help Scout Docs
Intercom read as Intercom Articles
ServiceNow read as ServiceNow Knowledge Management
Zendesk read as Zendesk Guide
Zendesk Suite read as Zendesk Guide
Unresolved, counted raw
Echo Knowledge Base
Freshdesk AI
GitHub Wiki
Jira Service Management KB + Confluence
Knowledgetree
MS Teams Files
Microsooft SharePoint
Slab or Slite
Squibler
WeDocs
Zoho
Zoho Assist
Discontinued, still offered
No shut-down product was recommended here.